{"693622":{"#nid":"693622","#data":{"type":"news","title":"Researchers Find Architectural Backdoors in AI Models Are Harder to Exploit in the Real World","body":[{"value":"\u003Cp\u003EImagine a vehicle powered by artificial intelligence (AI) whose object detection system has been secretly modified to misidentify stop signs whenever a particular visual pattern appears in its camera feed.\u003C\/p\u003E\u003Cp\u003EUnlike traditional AI backdoors, which manipulate a model\u0027s learned parameters, architectural backdoors hide malicious instructions directly in the code that defines how the model operates.\u003C\/p\u003E\u003Cp\u003EHowever, everyday image-processing operations, such as cropping, adjusting contrast, or adding noise, can change a trigger pattern and prevent an attack from working, according to \u003Ca href=\u0022https:\/\/davidoygenblik.github.io\/pdfs\/FAULT.pdf\u0022\u003Enew research\u003C\/a\u003E from Georgia Tech.\u003C\/p\u003E\u003Cp\u003EThe findings challenge assumptions about how practical these attacks are. Although previous research showed that architectural backdoors could work under controlled conditions, the Georgia Tech team found that existing approaches struggle to remain effective and difficult to detect when AI systems process images under realistic conditions.\u003C\/p\u003E\u003Cp\u003E\u201cThe biggest misconception is that demonstrating an architectural backdoor under controlled conditions means it will actually work in the real world,\u201d said \u003Cstrong\u003EDavid Oygenblik\u003C\/strong\u003E, Ph.D. student and lead author of the study.\u003C\/p\u003E\u003Cp\u003EThe study details the development of FAULT, a framework for evaluating architectural backdoors under realistic conditions.\u003C\/p\u003E\u003Cp\u003EThe findings reveal a tradeoff. Attackers can make a backdoor more sensitive, so it recognizes its trigger after an image has been changed. But that also increases the chance that ordinary images will accidentally activate the backdoor, potentially hurting the AI system\u2019s performance.\u003C\/p\u003E\u003Cp\u003E\u201cFor the architectural backdoors we study, this tradeoff is fundamental,\u201d Oygenblik said.\u003C\/p\u003E\u003Cp\u003EThe team found that this problem persisted across five methods of implementing architectural backdoors. Even when attackers knew how the system would process images, they struggled to make their attacks both reliable and difficult to detect.\u003C\/p\u003E\u003Cp\u003EThe research did not test attacks against real vehicles or other production systems, nor did it demonstrate outcomes such as crashes or ransomware. Instead, it examined whether existing architectural backdoors could reliably activate under different image-processing conditions.\u003C\/p\u003E\u003Cp\u003EHowever, the findings highlight a potential risk in the AI software supply chain. If an attacker inserted malicious code into an AI model used in a real system, the backdoor could potentially cause incorrect predictions when its trigger was detected. The consequences would depend on how the system used the model\u2019s output.\u003C\/p\u003E\u003Cp\u003EBecause architectural backdoors hide in code, examining a model\u2019s learned parameters or retraining it may not be enough to uncover or remove the threat.\u003C\/p\u003E\u003Cp\u003EOygenblik said developers should test AI systems under realistic conditions, watch for unexpected drops in accuracy, and examine model code for suspicious trigger-detection logic.\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/davidoygenblik.github.io\/pdfs\/FAULT.pdf\u0022\u003E\u003Cem\u003EFinding FAULTs in Architectural Backdoors: Why Trigger Detection Fails Under Real-World Conditions\u003C\/em\u003E\u003C\/a\u003E, was accepted to the \u003Ca href=\u0022https:\/\/sigsac.org\/ccs\/CCS2026\/\u0022\u003EACM Conference on Computer and Communications Security\u003C\/a\u003E. The authors will present the paper in The Hague in November.\u003C\/p\u003E\u003Cp\u003EOygenblik conducted the research with undergraduate students \u003Cstrong\u003ETeja Akella\u003C\/strong\u003E and \u003Cstrong\u003ETanmay Gupta\u003C\/strong\u003E, Ph.D. student \u003Cstrong\u003EYizhi Huang,\u003C\/strong\u003E and Associate Professor \u003Cstrong\u003EBrendan Saltaformaggio\u003C\/strong\u003E of Georgia Tech\u2019s \u003Ca href=\u0022https:\/\/cyfi.ece.gatech.edu\/\u0022\u003ECyber Forensics Innovation Laboratory\u003C\/a\u003E. The lab is a collaboration between the \u003Ca href=\u0022https:\/\/scp.cc.gatech.edu\/\u0022\u003ESchool of Cybersecurity and Privacy\u003C\/a\u003E and the \u003Ca href=\u0022https:\/\/ece.gatech.edu\/\u0022\u003ESchool of Electrical and Computer Engineering\u003C\/a\u003E.\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EArchitectural backdoors in AI models appear harder to exploit reliably under real-world image processing. Georgia Tech researchers developed FAULT to evaluate these threats beyond controlled demonstrations.\u003C\/p\u003E\u003Cp\u003E\u2022\u2002Cropping, contrast changes, and similar transformations can disrupt visual triggers across five backdoor methods.\u003Cbr\u003E\u2022\u2002Increasing trigger sensitivity improves reliability but also raises accidental activations and may reduce system performance.\u003Cbr\u003E\u2022\u2002The study warns that parameter inspection or retraining may miss code-based threats, urging realistic testing and code reviews for suspicious trigger logic.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Architectural backdoors in AI models appear harder to exploit reliably under real-world image processing. Georgia Tech researchers developed FAULT to evaluate these threats beyond controlled demonstrations."}],"uid":"36253","created_gmt":"2026-10-29 17:11:18","changed_gmt":"2026-10-29 17:16:10","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-10-29T00:00:00-04:00","iso_date":"2026-10-29T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681594":{"id":"681594","type":"image","title":"Car-security.png","body":null,"created":"1793293918","gmt_created":"2026-10-29 17:11:58","changed":"1793293918","gmt_changed":"2026-10-29 17:11:58","alt":"A digital car with a lock on the top of it ","file":{"fid":"266018","name":"Car-security.png","image_path":"\/sites\/default\/files\/2026\/10\/29\/Car-security.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/29\/Car-security.png","mime":"image\/png","size":758850,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/29\/Car-security.png?itok=cyR93DUW"}}},"media_ids":["681594"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"660406","name":"School of Cybersecurity \u0026 Privacy"},{"id":"660367","name":"School of Cybersecurity and Privacy"}],"categories":[{"id":"194606","name":"Artificial Intelligence"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"135","name":"Research"},{"id":"8862","name":"Student Research"}],"keywords":[],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"145171","name":"Cybersecurity"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJohn Popham\u003C\/p\u003E\u003Cp\u003ECommunications Officer for the School of Cybersecurity and Privacy\u003C\/p\u003E","format":"limited_html"}],"email":["jpopham3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}},"693211":{"#nid":"693211","#data":{"type":"news","title":"Deleted AI Chats May Leave Clues Behind","body":[{"value":"\u003Cp\u003EDeleting a conversation with an artificial intelligence (AI) assistant may not erase everything the assistant remembers.\u003C\/p\u003E\u003Cp\u003EGeorgia Tech researchers have developed a tool that can recover deleted conversations from AI assistants running on Android phones. The tool, called \u003Ca href=\u0022https:\/\/ieeexplore.ieee.org\/abstract\/document\/11573549\u0022\u003EORISA\u003C\/a\u003E, can also rebuild the recovered information into a working AI session.\u003C\/p\u003E\u003Cp\u003EThe findings show that deleting an AI conversation on a phone does not necessarily mean it removes every trace.\u003C\/p\u003E\u003Cp\u003EThe research could give digital investigators a new way to recover information from phones. It also raises privacy concerns for people who use AI assistants that run locally on their devices.\u003C\/p\u003E\u003Cp\u003ELocal AI assistants run directly on a phone rather than sending conversations to a cloud service. While the local assistant is running, information from conversations can remain in the phone\u2019s working memory even after it is deleted.\u003C\/p\u003E\u003Cp\u003EORISA searches this memory for pieces of deleted conversations.\u003C\/p\u003E\u003Cp\u003EIn one experiment, researchers created a fictional AI assistant called \u201cProject Note Keeper\u201d using the ChatterUI Android app. They gave it 100 fictional facts about a project, then deleted the conversation.\u003C\/p\u003E\u003Cp\u003EORISA recovered information from the deleted conversation and used it to create a new working session. When researchers asked the restored assistant to list the project notes it had been given, it returned 26 facts. The original session could access only 14 facts because the rest had fallen outside its active memory.\u003C\/p\u003E\u003Cp\u003EThe experiment showed that researchers could recover information the AI had already stopped actively using.\u003C\/p\u003E\u003Cp\u003E\u201cIt can help establish what information someone shared with an AI assistant and what assistance they received,\u201d said Ph.D. student \u003Cstrong\u003EKen Xu\u003C\/strong\u003E, lead author of the study.\u003C\/p\u003E\u003Cp\u003EThe researchers tested ORISA with 10 Android apps and three AI models. Across 60 test configurations, the tool recovered conversation information that remained in the phone\u2019s memory.\u003C\/p\u003E\u003Cp\u003EThe researchers say the information becomes harder to recover as the phone\u2019s memory is overwritten by other activity.\u003C\/p\u003E\u003Cp\u003EThe research was presented at the 2026 IEEE Symposium on Security and Privacy. The paper, titled \u003Cem\u003ERecovering and Rehosting Mobile Local LLM Conversations and Contexts via Memory Forensics,\u0026nbsp;\u003C\/em\u003Ewas authored by Ph.D. students Xu, \u003Cstrong\u003EDavid Oygenblik\u003C\/strong\u003E, \u003Cstrong\u003ERunze Zhang\u003C\/strong\u003E, and \u003Cstrong\u003EMingxuan Yao\u003C\/strong\u003E; Research Scientist \u003Cstrong\u003EMuhammad Ibrahim\u003C\/strong\u003E; and Associate Professor \u003Cstrong\u003EBrendan\u003C\/strong\u003E \u003Cstrong\u003ESaltaformaggio\u003C\/strong\u003E. The work was done in Georgia Tech\u0027s \u003Ca href=\u0022https:\/\/cyfi.ece.gatech.edu\/\u0022\u003ECyber Forensics Innovation Laboratory\u003C\/a\u003E, a collaboration between the \u003Ca href=\u0022https:\/\/scp.cc.gatech.edu\/\u0022\u003ESchool of Cybersecurity and Privacy\u003C\/a\u003E and the \u003Ca href=\u0022https:\/\/www.ece.gatech.edu\/\u0022\u003ESchool of Electrical and Computer Engineering\u003C\/a\u003E.\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EDeleting a locally stored AI conversation may remove it from view without eliminating its data. Researchers find that deleted local AI chats may remain recoverable from a phone\u2019s memory through a new tool called ORISA. ORISA recovered 26 of 100 project facts from a deleted Android AI session\u2014more than the original session could still access. This shows that information an assistant appears to have forgotten may remain forensically recoverable.\u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Researchers find that deleted local AI chats may remain recoverable from a phone\u2019s memory through a new tool called ORISA."}],"uid":"36253","created_gmt":"2026-10-13 12:45:52","changed_gmt":"2026-10-26 12:59:02","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-10-13T00:00:00-04:00","iso_date":"2026-10-13T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681416":{"id":"681416","type":"image","title":"Cyfi-Lab-Brendan-and-Student.jpg","body":null,"created":"1791895736","gmt_created":"2026-10-13 12:48:56","changed":"1791895736","gmt_changed":"2026-10-13 12:48:56","alt":"A man points to a rack of CPUs. He is talking to a student who is slighlty out of focus. ","file":{"fid":"265819","name":"Cyfi-Lab-Brendan-and-Student.jpg","image_path":"\/sites\/default\/files\/2026\/10\/13\/Cyfi-Lab-Brendan-and-Student.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/13\/Cyfi-Lab-Brendan-and-Student.jpg","mime":"image\/jpeg","size":362068,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/13\/Cyfi-Lab-Brendan-and-Student.jpg?itok=zg3onBN9"}}},"media_ids":["681416"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"660406","name":"School of Cybersecurity \u0026 Privacy"},{"id":"660367","name":"School of Cybersecurity and Privacy"}],"categories":[{"id":"194606","name":"Artificial Intelligence"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"145171","name":"Cybersecurity"}],"news_room_topics":[{"id":"71881","name":"Science and Technology"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003E\u003Ca href=\u0022mailto:jpopham3@gatech.edu\u0022\u003EJohn Popham\u003C\/a\u003E\u003Cbr\u003ECommunications Officer\u003Cbr\u003ESchool of Cybersecurity and Privacy\u003Cbr\u003EGeorgia Tech\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}},"693212":{"#nid":"693212","#data":{"type":"news","title":"Small Farmers Being Weighed Down by Food Traceability Rule, New Paper Finds","body":[{"value":"\u003Cp\u003EThe Food and Drug Administration\u2019s (FDA)\u0026nbsp;\u003Ca href=\u0022https:\/\/www.fda.gov\/media\/183514\/download\u0022\u003EFood Traceability Rule\u003C\/a\u003E requires producers and distributors of perishable foods to submit electronic data records during a contamination outbreak.\u003C\/p\u003E\u003Cp\u003EHowever, a new paper by a Georgia Tech-led research team suggests that the requirements can disproportionately burden family farms and other small food producers due to a lack of technological infrastructure, resources, or compliance expertise.\u003C\/p\u003E\u003Cp\u003EThe rule is mandated by Section 204(d) of the Food Safety Modernization Act, which Congress passed and President Barack Obama signed into law in 2011. Intended to help the FDA quickly identify the source of contamination, the rule requires producers or distributors with more than $25,000 in annual produce sales to comply or face significant fines.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEarlier this year, the FDA extended its compliance deadline to July 2028. One reason for the extension may be the volume of feedback from stakeholders affected by the rule. The FDA received more than 1,200 comments during an open forum, with feedback from stakeholders ranging from major distributors to small farmers.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cMany small farmers commented on how they may not have the devices needed to input this data,\u201d said\u0026nbsp;\u003Ca href=\u0022https:\/\/www.kwonsoonho.com\/\u0022\u003E\u003Cstrong\u003ESoonho Kwon\u003C\/strong\u003E\u003C\/a\u003E, a Ph.D. student in Georgia Tech\u2019s School of Interactive Computing (SIC) and lead author of the paper. \u201cDoes this mean they have to purchase it themselves? Do they need to become educated on how to use computing systems?\u201d\u003C\/p\u003E\u003Cp\u003EKwon is a member of the\u0026nbsp;\u003Ca href=\u0022https:\/\/sites.google.com\/view\/escapelab?pli=1\u0026amp;authuser=0\u0022\u003EEquity and Sustainability in Computing Lab\u003C\/a\u003E, which is led by SIC professor and chair\u0026nbsp;\u003Ca href=\u0022https:\/\/shaowenbardzell.com\/about\/\u0022\u003E\u003Cstrong\u003EShaowen Bardzell\u003C\/strong\u003E\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003EMany small farms also said they can\u2019t afford to hire someone to track the data.\u003C\/p\u003E\u003Cp\u003EOne small farmer said the amount of data tracking required by the rule is overwhelming. Some of the required data include:\u003C\/p\u003E\u003Cul\u003E\u003Cli data-list-item-id=\u0022ea1cd1b17babad7a094193ce3cfcdc1e5\u0022\u003Elocation and name of the field where food was harvested\u003C\/li\u003E\u003Cli data-list-item-id=\u0022e3e0b858de04d537ed1544ed215d6a3ca\u0022\u003Edate of harvest\u003C\/li\u003E\u003Cli data-list-item-id=\u0022e513b4f8aa9e9d9f23b57363206857f61\u0022\u003Epacking dates\u003C\/li\u003E\u003Cli data-list-item-id=\u0022e619ee0212b73538d858d6c2bed7b8f07\u0022\u003Eshipping dates\u003C\/li\u003E\u003C\/ul\u003E\u003Cp\u003E\u201cPlease do not force us to do technology stuff,\u201d the commenter said. \u201cIt\u2019s hard enough to keep up with the local demand as it is. We run a pretty low digital technology effort. It\u2019s basically harvest fresh organically grown veggies and sell them to local people.\u201d\u003C\/p\u003E\u003Cp\u003EKwon said the intention of the Food Traceability Rule is admirable.\u003C\/p\u003E\u003Cp\u003E\u201cPreventing foodborne illness is critical, and data- and technology-driven governance can be a powerful tool toward that goal,\u201d he said. \u201cBut it\u2019s equally important to think critically about who is supposed to be the default user of these systems, and who gets missed in the process. It\u2019s undermining the people who are unable to comply.\u201d\u003C\/p\u003E\u003Cp\u003EOther factors didn\u2019t appear to be considered by the FDA, including the lack of technological infrastructure in rural America, where many foods are grown.\u003C\/p\u003E\u003Cp\u003E\u201cMany parts of rural America have limited or unreliable internet access,\u201d Kwon said. \u201cIf the FDA wants them to send this data, they must comply within 24 hours. Does that mean they have to stop their daily routine and drive to a city that has internet to send it? The rule is operating on the assumption that everyone is dealing with the same physical environment.\u201d\u003C\/p\u003E\u003Cp\u003ECulture and religion also seem overlooked. Some commenters raised concerns that Amish farmers who avoid certain technologies for religious reasons would be pressured into digital record keeping.\u003C\/p\u003E\u003Cp\u003EMany major distributors and organizations expressed support for the Food Traceability Rule in the FDA\u2019s forum.\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cathwieczorek.com\/\u0022\u003E\u003Cstrong\u003ECatherine Wieczorek\u003C\/strong\u003E\u003C\/a\u003E, a Ph.D. student in SIC and co-author on the paper, said these organizations don\u2019t have the same tension points as smaller producers.\u003C\/p\u003E\u003Cp\u003E\u201cLarger food producers have the operational capacity to do the type of work the rule requires,\u201d Wieczorek said. \u201cWe find there\u2019s a power imbalance when it comes to smaller food producers like a family farm. Change at that scale is difficult for smaller producers.\u201d\u003C\/p\u003E\u003Cp\u003EBardzell, who advises Kwon and Wieczorek, said the situation provides computing researchers an opportunity to create interventions that will benefit those with fewer resources.\u003C\/p\u003E\u003Cp\u003E\u201cIn a data age when we\u2019re adding AI into our work processes and labor practices, we need to think about how this need creates unequal burdens on different stakeholders in our food system,\u201d Bardzell said. \u201cIt\u2019s a significant challenge for computing going forward.\u201d\u003C\/p\u003E\u003Cp\u003EKwon will present the paper on behalf of his collaborators next week at the\u0026nbsp;\u003Ca href=\u0022https:\/\/cscw.acm.org\/2026\/\u0022\u003EACM Conference on Computer-Supported Cooperative Work and Social Computing\u003C\/a\u003E (CSCW) in Salt Lake City, Utah. Their research is supported by the National Science Foundation.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EA new paper by a Georgia Tech-led research team suggests that the FDA\u0027s Food Traceability Rule can disproportionately burden family farms and other small food producers due to a lack of technological infrastructure, resources, or compliance expertise.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"A new paper by a Georgia Tech-led research team suggests that the FDA\u0027s Food Traceability Rule can disproportionately burden family farms and other small food producers due to a lack of technological infrastructure, resources, or compliance expertise."}],"uid":"36530","created_gmt":"2026-10-13 14:42:39","changed_gmt":"2026-10-26 12:58:29","author":"Nathan Deen","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-10-13T00:00:00-04:00","iso_date":"2026-10-13T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681417":{"id":"681417","type":"image","title":"AdobeStock_615559252.jpeg","body":null,"created":"1791902571","gmt_created":"2026-10-13 14:42:51","changed":"1791902571","gmt_changed":"2026-10-13 14:42:51","alt":"A farmer holds a tablet while a woman to his right assists him","file":{"fid":"265820","name":"AdobeStock_615559252.jpeg","image_path":"\/sites\/default\/files\/2026\/10\/13\/AdobeStock_615559252.jpeg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/13\/AdobeStock_615559252.jpeg","mime":"image\/jpeg","size":129552,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/13\/AdobeStock_615559252.jpeg?itok=pcEMK4t4"}}},"media_ids":["681417"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"50876","name":"School of Interactive Computing"}],"categories":[{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"194609","name":"Industry"},{"id":"8862","name":"Student Research"}],"keywords":[],"core_research_areas":[{"id":"39501","name":"People and Technology"}],"news_room_topics":[{"id":"71901","name":"Society and Culture"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}},"693264":{"#nid":"693264","#data":{"type":"news","title":"When a Ship\u2019s Systems Lie, Cybersecurity Gets Complicated","body":[{"value":"\u003Cp\u003ESailors at sea rely on electronic equipment to keep ships on course and out of danger, but what happens when hackers get involved? Are the mariners equipped to handle modern cybersecurity threats like GPS spoofing?\u003C\/p\u003E\u003Cp\u003EIn a \u003Ca href=\u0022https:\/\/arxiv.org\/pdf\/2609.12810\u0022\u003Estudy\u003C\/a\u003E accepted for the 2026 \u003Ca href=\u0022https:\/\/www.sigsac.org\/ccs\/CCS2026\/index.html\u0022\u003EACM Conference on Computer and Communications Security\u003C\/a\u003E, Georgia Tech researchers interviewed 20 military sailors about their cybersecurity experiences, training, and responses to hypothetical scenarios. Their findings point to a gap between how mariners are trained to handle emergencies and how cyberattacks can compromise the systems they depend on.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe study found several gaps in how crews prepare for cyber threats:\u003C\/p\u003E\u003Cul\u003E\u003Cli data-list-item-id=\u0022edf63c815360cecb04c01d6561be9a7b1\u0022\u003ETraining often misses the mark. Thirteen participants said that standard cybersecurity training was largely irrelevant to their shipboard duties, and 14 reported receiving no mission-specific cybersecurity training.\u003C\/li\u003E\u003Cli data-list-item-id=\u0022e619f896d048b6bcd034a76176e6067bb\u0022\u003EOperational technology is often overlooked. Eighteen participants said their training did not distinguish between traditional information technology and operational technology, such as navigation and propulsion systems.\u003C\/li\u003E\u003Cli data-list-item-id=\u0022e928f3fef211e61dcd97e963697bd9389\u0022\u003EObvious failures are easier to recognize. Eighteen participants said they would primarily look for visible signs of operational problems when identifying a potential cyberattack.\u003C\/li\u003E\u003Cli data-list-item-id=\u0022e1499170bf08bd8a760ed09fee3a091d7\u0022\u003ECybersecurity is often a low priority. Seventeen participants described their cybersecurity training as absent, low quality, or a low priority.\u003C\/li\u003E\u003C\/ul\u003E\u003Cp\u003EThese gaps matter because cyberattacks can compromise a system without causing it to stop working. For example, an attacker could manipulate navigation data, leaving a crew to make decisions based on false information.\u003C\/p\u003E\u003Cp\u003E\u201cI\u2019d assume it was anything but cyber at first. It would probably take me quite some time to get to that conclusion,\u201d one participant told the researchers.\u003C\/p\u003E\u003Cp\u003EThe team examined three hypothetical scenarios: GPS spoofing, loss of propulsion control in a high-traffic area, and failure of electronic navigation systems in a congested channel at night.\u003C\/p\u003E\u003Cp\u003EIn each scenario, mariners would first focus on keeping the vessel safe, using established procedures to stabilize the ship and troubleshoot its systems. While this response is essential during an emergency, it could delay recognition of an attack if crews do not consider that the system or its data may have been compromised.\u003C\/p\u003E\u003Cp\u003EFor example, a ship navigating a narrow channel depends on accurate location information, but what happens when its navigation systems appear to work normally while a hacker manipulates that data?\u003C\/p\u003E\u003Cp\u003EAn attacker could use GPS spoofing to falsify a vessel\u2019s reported position. If the false position is close enough to the ship\u2019s actual location, a mariner might not notice anything wrong. The vessel could gradually head toward shallow water or another obstacle without triggering an obvious error or alarm.\u003C\/p\u003E\u003Cp\u003E\u201cBy the time the mariner realizes something is wrong, the ship\u2019s size and limited maneuverability could make it too late to avoid a grounding or collision,\u201d said \u003Cstrong\u003EAnna Raymaker\u003C\/strong\u003E, a Georgia Tech Ph.D. student who studies maritime security.\u003C\/p\u003E\u003Cp\u003EThe scenario illustrates a central challenge in maritime cybersecurity: An equipment failure may be easy to recognize, but a cyberattack that provides false information can be much harder to detect.\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/arxiv.org\/pdf\/2609.12810\u0022\u003E\u003Cem\u003EBatten the Hatches: Cybersecurity with Military Mariners\u003C\/em\u003E\u003C\/a\u003E\u003Cem\u003E\u0026nbsp;\u003C\/em\u003Ewas written by master\u2019s student \u003Cstrong\u003ERyan Von Brock\u003C\/strong\u003E, Raymaker, Research Scientist \u003Cstrong\u003EAnimesh Chhotaray\u003C\/strong\u003E, Associate Professors \u003Cstrong\u003EFrank Li\u003C\/strong\u003E and \u003Cstrong\u003ESaman Zonouz\u003C\/strong\u003E, and Provost \u0026amp; Executive Vice President for Academic Affairs \u003Cstrong\u003ERaheem Beyah\u003C\/strong\u003E.\u003C\/p\u003E\u003Cp\u003EThe research was conducted in Georgia Tech\u2019s \u003Ca href=\u0022https:\/\/sites.gatech.edu\/capcpsec\/\u0022\u003ECyber-Physical Security Lab\u003C\/a\u003E, a collaboration between the \u003Ca href=\u0022https:\/\/scp.cc.gatech.edu\/\u0022\u003ESchool of Cybersecurity and Privacy\u003C\/a\u003E and the \u003Ca href=\u0022https:\/\/ece.gatech.edu\/\u0022\u003ESchool of Electrical and Computer Engineering\u003C\/a\u003E.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EPhotos by Terence Rushin\/College of Computing\u003C\/em\u003E\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EMaritime cybersecurity training leaves sailors vulnerable to attacks that manipulate ship systems without obvious failures. The Georgia Tech study identifies weaknesses in preparation and threat recognition among military mariners. Interviews with 20 military sailors found that 13 considered standard training irrelevant, while 14 lacked mission-specific cybersecurity training. Operational technology gaps affected 18 participants, and 18 said they would mainly seek visible operational problems when detecting attacks. In scenarios involving GPS spoofing and navigation or propulsion failures, crews prioritized vessel safety, but false data could delay detection and cause grounding or collision.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Maritime cybersecurity training leaves sailors vulnerable to attacks that manipulate ship systems without obvious failures. The Georgia Tech study identifies weaknesses in preparation and threat recognition among military mariners."}],"uid":"36253","created_gmt":"2026-10-16 13:29:06","changed_gmt":"2026-10-26 12:57:00","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-10-16T00:00:00-04:00","iso_date":"2026-10-16T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681456":{"id":"681456","type":"image","title":"Saman-Zonouz-Lab_banner.jpg","body":null,"created":"1792414735","gmt_created":"2026-10-19 12:58:55","changed":"1792414735","gmt_changed":"2026-10-19 12:58:55","alt":"A group photo of students and faculty standing around lab equipment found on a ship. ","file":{"fid":"265864","name":"Saman-Zonouz-Lab_banner.jpg","image_path":"\/sites\/default\/files\/2026\/10\/19\/Saman-Zonouz-Lab_banner.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/19\/Saman-Zonouz-Lab_banner.jpg","mime":"image\/jpeg","size":1807296,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/19\/Saman-Zonouz-Lab_banner.jpg?itok=C77DD-Gm"}},"681458":{"id":"681458","type":"image","title":"Saman-Zonouz-Lab_side-view.jpg","body":null,"created":"1792414735","gmt_created":"2026-10-19 12:58:55","changed":"1792414735","gmt_changed":"2026-10-19 12:58:55","alt":"A group of students working on lab equipment. The equipment replicates a ship\u0027s helm. ","file":{"fid":"265866","name":"Saman-Zonouz-Lab_side-view.jpg","image_path":"\/sites\/default\/files\/2026\/10\/19\/Saman-Zonouz-Lab_side-view.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/19\/Saman-Zonouz-Lab_side-view.jpg","mime":"image\/jpeg","size":1676397,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/19\/Saman-Zonouz-Lab_side-view.jpg?itok=-Potoyjw"}},"681457":{"id":"681457","type":"image","title":"Saman-Zonouz-Lab_ship-equipment.jpg","body":null,"created":"1792414735","gmt_created":"2026-10-19 12:58:55","changed":"1792414735","gmt_changed":"2026-10-19 12:58:55","alt":"Lab equipment of a ship steering wheel and other electronic  measuring devices. ","file":{"fid":"265865","name":"Saman-Zonouz-Lab_ship-equipment.jpg","image_path":"\/sites\/default\/files\/2026\/10\/19\/Saman-Zonouz-Lab_ship-equipment.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/19\/Saman-Zonouz-Lab_ship-equipment.jpg","mime":"image\/jpeg","size":1781292,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/19\/Saman-Zonouz-Lab_ship-equipment.jpg?itok=mkKyqYFy"}}},"media_ids":["681456","681458","681457"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"660406","name":"School of Cybersecurity \u0026 Privacy"},{"id":"660367","name":"School of Cybersecurity and Privacy"}],"categories":[{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"145","name":"Engineering"},{"id":"147","name":"Military Technology"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[],"core_research_areas":[{"id":"145171","name":"Cybersecurity"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[{"id":"71881","name":"Science and Technology"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003E\u003Ca href=\u0022mailto:jpopham3@gatech.edu\u0022\u003EJohn Popham\u003C\/a\u003E\u003Cbr\u003ECommunications Officer\u003Cbr\u003ESchool of Cybersecurity and Privacy\u003Cbr\u003EGeorgia Tech\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}},"693317":{"#nid":"693317","#data":{"type":"news","title":"Georgia Tech Researchers Find a Way to Reduce AI Chatbots\u2019 Reinforcement of Delusions","body":[{"value":"\u003Cp\u003EArtificial intelligence (AI) chatbots can give people a comfortable place to discuss personal thoughts and feelings. However, when a chatbot constantly agrees with a user, it can reinforce false beliefs and potentially \u003Ca href=\u0022https:\/\/www.theatlantic.com\/technology\/2025\/12\/ai-psychosis-is-a-medical-mystery\/685133\/?gift=rYkYJRkiFfFnni2r6QoYhEoKOopttUMYKvO0wk3NqmY\u0026amp;utm_source=copy-link\u0026amp;utm_medium=social\u0026amp;utm_campaign=share\u0022\u003Ecause harm\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/dl.acm.org\/doi\/10.1145\/3849709\u0022\u003ENew research\u003C\/a\u003E from Georgia Tech suggests that a simple change to a chatbot\u2019s instructions could reduce that risk. The work was accepted to the \u003Ca href=\u0022https:\/\/dl.acm.org\/doi\/10.1145\/3849709\u0022\u003EACM AI Letters\u003C\/a\u003E publication.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EResearchers \u003Cstrong\u003ELorenzo de la Loza\u003C\/strong\u003E and \u003Cstrong\u003EVijay Madisetti\u003C\/strong\u003E tested eight AI models in 1,280 experiments involving simulated conversations about delusional beliefs. They found that instructions designed to discourage excessive agreement reduced the models\u2019 confirmation of those beliefs by 73.8%. Adding a self-reflection step increased the reduction to 77%.\u003C\/p\u003E\u003Cp\u003E\u201cWe think that this paper will help AI providers and solution creators better understand how best to protect and safeguard their users from harming themselves,\u201d Madisetti said. \u201cThis may make AI safer for all of us.\u201d\u003C\/p\u003E\u003Cp\u003EAI chatbots are designed to be helpful and supportive. But that behavior can become risky when a chatbot agrees with a user\u2019s beliefs without questioning whether they reflect reality. Researchers call this behavior sycophancy.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECourtney Crooks\u003C\/strong\u003E, a principal research scientist at the \u003Ca href=\u0022https:\/\/gtri.gatech.edu\/\u0022\u003EGeorgia Tech Research Institute\u003C\/a\u003E and adjunct faculty member in Georgia Tech\u2019s \u003Ca href=\u0022https:\/\/scp.cc.gatech.edu\/\u0022\u003ESchool of Cybersecurity and Privacy\u003C\/a\u003E, said chatbot conversations can have both positive and negative effects.\u003C\/p\u003E\u003Cp\u003EPeople may feel more comfortable discussing difficult thoughts with a chatbot than with another person. But if the chatbot always agrees, users may miss opportunities to question their beliefs or consider other points of view.\u003C\/p\u003E\u003Cp\u003EThe same behavior that makes a chatbot feel supportive, Crooks explained, can also encourage harmful patterns of thinking.\u003C\/p\u003E\u003Cp\u003EThe researchers tested instructions that told AI models not to reinforce users\u2019 beliefs simply to be agreeable. The team evaluated the models using 16 clinically derived scenarios involving delusional beliefs.\u003C\/p\u003E\u003Cp\u003EThe team also tested other safety tools, including systems designed to flag potentially harmful content. The results suggest that changing a chatbot\u2019s instructions can be an effective way to reduce excessive agreement in the scenarios tested.\u003C\/p\u003E\u003Cp\u003ECrooks called the findings a promising direction for future research combining psychology and AI safety.\u003C\/p\u003E\u003Cp\u003EThe study did not test people in clinical settings or prove that the approach prevents real-world harm. However, it offers developers a potential way to make chatbots more careful when responding to vulnerable users without building an entirely new AI model.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EGeorgia Tech researchers found that instruction changes can reduce chatbots\u2019 reinforcement of delusional beliefs. The study suggests a practical safety measure while noting its real-world limits.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Georgia Tech researchers found that instruction changes can reduce chatbots\u2019 reinforcement of delusional beliefs."}],"uid":"36253","created_gmt":"2026-10-20 14:31:00","changed_gmt":"2026-10-26 12:55:58","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-10-20T00:00:00-04:00","iso_date":"2026-10-20T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681502":{"id":"681502","type":"image","title":"AI-Chatbot.jpg","body":null,"created":"1792602258","gmt_created":"2026-10-21 17:04:18","changed":"1792602258","gmt_changed":"2026-10-21 17:04:18","alt":"A person at a computer. A little digital robot is hovering near his fingers.","file":{"fid":"265912","name":"AI-Chatbot.jpg","image_path":"\/sites\/default\/files\/2026\/10\/21\/AI-Chatbot.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/21\/AI-Chatbot.jpg","mime":"image\/jpeg","size":1715464,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/21\/AI-Chatbot.jpg?itok=9cA4rhB2"}},"681478":{"id":"681478","type":"image","title":"Vijay.jpg","body":null,"created":"1792507064","gmt_created":"2026-10-20 14:37:44","changed":"1792507064","gmt_changed":"2026-10-20 14:37:44","alt":"A man in a suit speaking with two students. ","file":{"fid":"265888","name":"Vijay.jpg","image_path":"\/sites\/default\/files\/2026\/10\/20\/Vijay_0.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/20\/Vijay_0.jpg","mime":"image\/jpeg","size":1580263,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/20\/Vijay_0.jpg?itok=Dfwgw1z0"}}},"media_ids":["681502","681478"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"660406","name":"School of Cybersecurity \u0026 Privacy"},{"id":"660367","name":"School of Cybersecurity and Privacy"}],"categories":[{"id":"194606","name":"Artificial Intelligence"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[{"id":"192863","name":"go-ai"},{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"145171","name":"Cybersecurity"},{"id":"193653","name":"Georgia Tech Research Institute"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[{"id":"71881","name":"Science and Technology"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJohn Popham\u003C\/p\u003E\u003Cp\u003ECommunications Officer for the School of Cybersecurity and Privacy\u003C\/p\u003E","format":"limited_html"}],"email":["jpopham3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}},"693304":{"#nid":"693304","#data":{"type":"news","title":"Where Are They Now? Team Atlanta Takes AI Cybersecurity Beyond the Competition","body":[{"value":"\u003Cp\u003E\u003Ca href=\u0022https:\/\/team-atlanta.github.io\/\u0022\u003ETeam Atlanta\u003C\/a\u003E spent two years exploring how artificial intelligence (AI) could help identify and fix software security problems as part of the Defense Advanced Research Projects Agency (DARPA) \u003Ca href=\u0022https:\/\/sites.gatech.edu\/winningaixcc\/\u0022\u003EAI Cyber Challenge\u003C\/a\u003E (AIxCC).\u003C\/p\u003E\u003Cp\u003EAfter a grueling, world-class competition, the team \u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/news\/georgia-tech-makes-history-wins-darpa-challenge\u0022\u003Ewon\u003C\/a\u003E the $4 million first-place prize in August 2025.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe team has since disbanded. Some members have moved into the corporate world, while others continue in academia. Despite these varied paths, Team Atlanta\u2019s search for breakthrough AI cybersecurity solutions continues.\u003C\/p\u003E\u003Ch2\u003EFrom AIxCC to Microsoft\u003C\/h2\u003E\u003Cp\u003ETeam Atlanta lead \u003Cstrong\u003ETaesoo\u003C\/strong\u003E \u003Cstrong\u003EKim\u003C\/strong\u003E, principal security researcher \u003Cstrong\u003EDongkwan\u003C\/strong\u003E \u003Cstrong\u003EKim\u003C\/strong\u003E, and three other former team members joined Microsoft Security after the competition, where they continue to work on AI and cybersecurity in the \u003Ca href=\u0022https:\/\/github.com\/microsoft\/forge-lab\u0022 target=\u0022_blank\u0022\u003EFrontier Offensive Research \u0026amp; Generative Exploitation (FORGE) Lab\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003EThe move has given the researchers an opportunity to apply concepts from AIxCC to real-world software. It has also exposed them to challenges that are difficult to replicate in a competition or research lab.\u003C\/p\u003E\u003Cp\u003EDongkwan Kim said that team members continue to share what they learned through research papers, reports, software, and benchmarks. At Microsoft, these lessons are tested against real customer code.\u003C\/p\u003E\u003Cp\u003EThis work led to \u003Ca href=\u0022https:\/\/www.microsoft.com\/en-us\/security\/blog\/2026\/05\/12\/defense-at-ai-speed-microsofts-new-multi-model-agentic-security-system-tops-leading-industry-benchmark\/\u0022\u003EMDASH\u003C\/a\u003E, Microsoft\u0027s multi-agent, multi-model system for vulnerability discovery and remediation. The system uses more than 100 AI agents to search for vulnerabilities, validate potential findings, and help develop fixes.\u003C\/p\u003E\u003Cp\u003ERather than asking a single AI model if a piece of code contains a vulnerability, MDASH can examine a problem using multiple agents. The system can also try to create an exploit to determine whether a potential vulnerability is real and reachable.\u003C\/p\u003E\u003Cp\u003EFor Dongkwan Kim and the other former Team Atlanta members at Microsoft, moving from AIxCC to MDASH showed how research can look different when applied to real software.\u003C\/p\u003E\u003Cp\u003E\u201cAIxCC was not an endpoint for Team Atlanta,\u201d he said. \u201cWe continue sharing what we learned through technical reports, papers, open artifacts, and benchmarks for vulnerability discovery and patching.\u201d\u003C\/p\u003E\u003Cp\u003EWorking with customer code introduced new challenges for the Microsoft team. The researchers had to consider security boundaries, existing development processes, how findings would be reviewed, and how vulnerabilities would be prioritized for action.\u003C\/p\u003E\u003Cp\u003EThese challenges created a new feedback loop between research and product development. The team took ideas from AIxCC, test them on real software, learn where they worked and where they fell short, and use those lessons to improve the system.\u003C\/p\u003E\u003Cp\u003EThe experience also showed that AI does not replace the need for cybersecurity experts. Human researchers are still needed to provide context, decide how to break down difficult problems, validate findings, understand attack paths, and determine the potential impact of a vulnerability.\u003C\/p\u003E\u003Cp\u003ETaesoo Kim, a professor in the \u003Ca href=\u0022https:\/\/scp.cc.gatech.edu\/\u0022\u003ESchool of Cybersecurity and Privacy\u003C\/a\u003E and vice president of security research at Microsoft, said the competition continues to influence the Microsoft team\u0027s work.\u003C\/p\u003E\u003Cp\u003E\u201cEvery single activity that we\u2019ve done at Microsoft was influenced by AIxCC,\u201d he said in a \u003Ca href=\u0022https:\/\/commandline.microsoft.com\/taesoo-kim-interview-mdash-security-research\/\u0022\u003E2026 interview with Microsoft\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003EThe work has continued to grow. In 2026, Microsoft introduced \u003Ca href=\u0022https:\/\/microsoft.ai\/models\/mai-cyber-1-flash\/\u0022\u003EMAI-Cyber-1-Flash\u003C\/a\u003E, an AI model built specifically for cybersecurity and designed to work with MDASH.\u003C\/p\u003E\u003Cp\u003EThe model is designed to handle many of MDASH\u0027s tasks while allowing larger AI models to focus on harder problems. Microsoft reported that replacing 80% of the models used by MDASH with MAI-Cyber-1-Flash increased its performance on the CyberGym benchmark from 88.4% to 95.95%.\u003C\/p\u003E\u003Cp\u003EThe benchmark includes more than 1,500 examples from 188 software projects. Microsoft also reported that the new setup can achieve similar performance at half the cost of the previous MDASH configuration.\u003C\/p\u003E\u003Cp\u003E\u201cAIxCC has sparked cybersecurity innovation across the globe, from frontier AI companies to small academic labs,\u201d said Taesoo Kim. \u201cIt is an incredibly exciting time to be working in AI-driven security engineering and research, as we see AI fundamentally reshape how we find and fix vulnerabilities at scale.\u201d\u003C\/p\u003E\u003Ch2\u003EContinuing the Research at Georgia Tech\u003C\/h2\u003E\u003Cp\u003EThe AIxCC experience also continues to shape cybersecurity research at Georgia Tech.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EJiho\u003C\/strong\u003E \u003Cstrong\u003EKim\u003C\/strong\u003E, a Georgia Tech Ph.D. student who was part of Team Atlanta\u0027s research efforts, said one of the biggest lessons he\u2019s brought back to campus was learning how AI and traditional security tools can work together.\u003C\/p\u003E\u003Cp\u003EOne of these tools is fuzzing. Fuzzing tests software with large numbers of inputs to detect unexpected behavior or security problems. Large language models (LLMs), meanwhile, can reason about code and help guide the search.\u003C\/p\u003E\u003Cp\u003EDuring the AIxCC competition, the Team Atlanta combined these ideas in \u003Ca href=\u0022https:\/\/dl.acm.org\/doi\/10.1145\/3832783.3834365\u0022\u003ECtxFuzz\u003C\/a\u003E, a system that uses an LLM to help guide fuzzing toward parts of software that may contain vulnerabilities.\u003C\/p\u003E\u003Cp\u003EThe research was submitted to the \u003Ca href=\u0022https:\/\/conf.researchr.org\/home\/ase-2026\u0022\u003EACM\/IEEE International Conference on Automated Software Engineering\u003C\/a\u003E, where it received the ACM Distinguished Paper Award.\u003C\/p\u003E\u003Cp\u003E\u201cSince AIxCC, we\u2019ve continued building on some of the core findings from our two-year journey with Team Atlanta,\u201d Jiho Kim said.\u003C\/p\u003E\u003Cp\u003E\u201cOne of the biggest lessons for us was understanding how LLMs and traditional fuzzing can work together in a mutually beneficial way, using each to overcome the limitations of the other and ultimately find more and deeper vulnerabilities.\u201d\u003C\/p\u003E\u003Cp\u003EThe researchers also wanted to make the lessons from AIxCC useful to other cybersecurity researchers.\u003C\/p\u003E\u003Cp\u003EThey created an \u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/news\/competition-community-how-team-atlantas-ai-cybersecurity-breakthrough-going-open-source\u0022\u003EOpen-Source Cyber Reasoning System Framework\u003C\/a\u003E (OSS-CRS) and CRSBench, which provides researchers and security professionals with ways to use, test, and build on technology developed through AIxCC.\u003C\/p\u003E\u003Cp\u003E\u201cWe\u2019ve also been focused on making the results of AIxCC useful to the broader security community,\u201d Kim said. \u201cWe created OSS-CRS and CRSBench so that researchers and practitioners can more easily use, reproduce, and build upon the capabilities and lessons from our AIxCC work.\u201d\u003C\/p\u003E\u003Cp\u003EThe team\u0027s research has also moved beyond identifying vulnerabilities. Researchers are studying how well AI models can understand and reason about computer code.\u003C\/p\u003E\u003Cp\u003EJiho Kim and his lab mates in the \u003Ca href=\u0022https:\/\/gts3.org\/\u0022\u003ESystems Software \u0026amp; Security Lab\u003C\/a\u003E developed COIN, a benchmark designed to test how well LLMs can reason about code. The work has been accepted to the \u003Ca href=\u0022https:\/\/2026.emnlp.org\/\u0022\u003E2026 Conference on Empirical Methods in Natural Language Processing\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003EThe Georgia Tech researchers are also developing additional benchmarks to study the various types of reasoning required for cybersecurity. They are using what they learn to create new datasets and methods for training AI models focused on cybersecurity.\u003C\/p\u003E\u003Cp\u003E\u201cWe\u2019re using what we learn from these benchmarks to train cybersecurity-focused models through new datasets and training methodologies,\u201d Jiho Kim said.\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EPhotos by John Popham\/College of Computing\u003C\/em\u003E\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ETeam Atlanta\u2019s AI cybersecurity work has advanced from a competition victory to real-world vulnerability discovery. Former members continue this work through Microsoft products and Georgia Tech research. Microsoft\u2019s MDASH uses more than 100 AI agents for vulnerability discovery, validation, exploitation testing, and remediation; MAI-Cyber-1-Flash raised CyberGym performance from 88.4% to 95.95% while reducing costs. Georgia Tech researchers combine large language models with fuzzing through CtxFuzz, which received an ACM Distinguished Paper Award, and released OSS-CRS, CRSBench, and COIN to advance cybersecurity research.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Team Atlanta\u2019s AI cybersecurity work has advanced from a competition victory to real-world vulnerability discovery. Former members continue this work through Microsoft products and Georgia Tech research."}],"uid":"36253","created_gmt":"2026-10-19 17:56:04","changed_gmt":"2026-10-20 13:38:47","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-10-20T00:00:00-04:00","iso_date":"2026-10-20T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"680033":{"id":"680033","type":"image","title":"AIxCC-2025-27-web-copy.jpg","body":null,"created":"1776880174","gmt_created":"2026-04-22 17:49:34","changed":"1776880174","gmt_changed":"2026-04-22 17:49:34","alt":"A group of people standing inside of a convention hall. ","file":{"fid":"264266","name":"AIxCC-2025-27-web-copy.jpg","image_path":"\/sites\/default\/files\/2026\/04\/22\/AIxCC-2025-27-web-copy.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/04\/22\/AIxCC-2025-27-web-copy.jpg","mime":"image\/jpeg","size":1078593,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/04\/22\/AIxCC-2025-27-web-copy.jpg?itok=6t8OfTPC"}},"681466":{"id":"681466","type":"image","title":"TeamAtlanta-Reception-15.jpg","body":null,"created":"1792432685","gmt_created":"2026-10-19 17:58:05","changed":"1792432685","gmt_changed":"2026-10-19 17:58:05","alt":"A crowd of people looking at a screen. The screen shows a team photo of Team Atlanta.","file":{"fid":"265874","name":"TeamAtlanta-Reception-15.jpg","image_path":"\/sites\/default\/files\/2026\/10\/19\/TeamAtlanta-Reception-15.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/19\/TeamAtlanta-Reception-15.jpg","mime":"image\/jpeg","size":2223190,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/19\/TeamAtlanta-Reception-15.jpg?itok=Uk3m9De-"}},"677708":{"id":"677708","type":"image","title":"Team Atlanta at DefCon 33","body":null,"created":"1755285635","gmt_created":"2025-08-15 19:20:35","changed":"1755285635","gmt_changed":"2025-08-15 19:20:35","alt":"Team Atlanta stands on the dark DefCon stage during the convention\u0027s closing ceremony. ","file":{"fid":"261641","name":"IMG_9163.jpg","image_path":"\/sites\/default\/files\/2025\/08\/15\/IMG_9163.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2025\/08\/15\/IMG_9163.jpg","mime":"image\/jpeg","size":2393783,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2025\/08\/15\/IMG_9163.jpg?itok=QL3hjg7_"}},"681468":{"id":"681468","type":"image","title":"AIxCC-2025-38.jpg","body":null,"created":"1792432817","gmt_created":"2026-10-19 18:00:17","changed":"1792432817","gmt_changed":"2026-10-19 18:00:17","alt":"A man standing with his hands out looking at the sky. ","file":{"fid":"265876","name":"AIxCC-2025-38.jpg","image_path":"\/sites\/default\/files\/2026\/10\/19\/AIxCC-2025-38.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/19\/AIxCC-2025-38.jpg","mime":"image\/jpeg","size":2528658,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/19\/AIxCC-2025-38.jpg?itok=XTCMKvSN"}},"681469":{"id":"681469","type":"image","title":"AIxCC-2025-42.jpg","body":null,"created":"1792432817","gmt_created":"2026-10-19 18:00:17","changed":"1792432817","gmt_changed":"2026-10-19 18:00:17","alt":"A man looking at the camera smiling. ","file":{"fid":"265877","name":"AIxCC-2025-42.jpg","image_path":"\/sites\/default\/files\/2026\/10\/19\/AIxCC-2025-42.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/19\/AIxCC-2025-42.jpg","mime":"image\/jpeg","size":5433378,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/19\/AIxCC-2025-42.jpg?itok=uc5jvAL_"}},"681470":{"id":"681470","type":"image","title":"AIxCC-2025-50.jpg","body":null,"created":"1792432817","gmt_created":"2026-10-19 18:00:17","changed":"1792432817","gmt_changed":"2026-10-19 18:00:17","alt":"A man looking up at a screen with his hands clasped in front of him.","file":{"fid":"265878","name":"AIxCC-2025-50.jpg","image_path":"\/sites\/default\/files\/2026\/10\/19\/AIxCC-2025-50.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/19\/AIxCC-2025-50.jpg","mime":"image\/jpeg","size":2962205,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/19\/AIxCC-2025-50.jpg?itok=ydXeVf8n"}},"681467":{"id":"681467","type":"image","title":"AIxCC-2025-05.jpg","body":null,"created":"1792432817","gmt_created":"2026-10-19 18:00:17","changed":"1792432817","gmt_changed":"2026-10-19 18:00:17","alt":"A trophy next to a virtual scoreboard. The scoreboard has virtual stats from the AIxCC competition. ","file":{"fid":"265875","name":"AIxCC-2025-05.jpg","image_path":"\/sites\/default\/files\/2026\/10\/19\/AIxCC-2025-05.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/10\/19\/AIxCC-2025-05.jpg","mime":"image\/jpeg","size":4251863,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/10\/19\/AIxCC-2025-05.jpg?itok=tfIiiSsD"}}},"media_ids":["680033","681466","677708","681468","681469","681470","681467"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"660406","name":"School of Cybersecurity \u0026 Privacy"},{"id":"660367","name":"School of Cybersecurity and Privacy"}],"categories":[{"id":"194606","name":"Artificial Intelligence"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[{"id":"192863","name":"go-ai"},{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"145171","name":"Cybersecurity"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJohn Popham\u003C\/p\u003E\u003Cp\u003ECommunications Officer at the School of Cybersecurity and Privacy\u003C\/p\u003E","format":"limited_html"}],"email":["jpopham3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}},"692926":{"#nid":"692926","#data":{"type":"news","title":"Cybersecurity Student Spends Summer of Securing the High Seas","body":[{"value":"\u003Cp\u003EWhen \u003Cstrong\u003EAnna\u003C\/strong\u003E \u003Cstrong\u003ERaymaker\u003C\/strong\u003E began her Ph.D. at Georgia Tech, she hadn\u0027t yet decided which area of cybersecurity she wanted to pursue. That changed when she began working on a boat test bed and \u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/news\/researchers-find-training-gaps-impacting-maritime-cybersecurity-readiness\u0022\u003Etalking\u003C\/a\u003E with mariners about the cybersecurity challenges they face at sea.\u003C\/p\u003E\u003Cp\u003EThose conversations led Raymaker to focus her research on maritime security, including vulnerabilities in the Automatic Identification System (AIS), which ships use to broadcast their location, speed, and course.\u003C\/p\u003E\u003Cp\u003EThis summer, Raymaker brought this research to Massachusetts Institute of Technology (MIT) \u003Ca href=\u0022https:\/\/www.ll.mit.edu\/\u0022\u003ELincoln Laboratory\u003C\/a\u003E, where she built a test bed to study AIS security in a controlled environment. The experience has also led to new research questions, from the security of shipboard Starlink connections to autonomous vessels and other maritime technologies.\u003C\/p\u003E\u003Cp\u003EWe spoke with Raymaker about her research, her experience at Lincoln Laboratory, and what she hopes to investigate next.\u003C\/p\u003E\u003Ch2\u003EWhat will you be working on at the MIT Lincoln Laboratory next?\u003C\/h2\u003E\u003Cp\u003EAfter submitting our paper based on this summer\u2019s work to a cybersecurity conference, we are continuing our collaboration and starting a new project to identify critical infrastructure that uses unique protocols. The project is still in the early stages of planning and design, but I\u2019m excited to continue working with the team.\u003C\/p\u003E\u003Ch2\u003EWhat was the biggest challenge you faced while building and testing the AIS security testbed, and how did you work through it?\u003C\/h2\u003E\u003Cp\u003EThe biggest challenge was getting equipment designed to be installed and operated on a boat to function properly in a lab setting. That meant using a Faraday cage so that our AIS transmissions and security experiments wouldn\u2019t accidentally broadcast to nearby ships or interfere with real maritime traffic. I also had to simulate GPS signals and set up additional hardware to trick the AIS transponders into thinking they were operating on a real vessel. Putting all those pieces together into a safe, realistic test bed was challenging, but it ultimately let us study the equipment in a controlled environment.\u003C\/p\u003E\u003Ch2\u003EYou mentioned the collaborative culture at Lincoln Laboratory. Can you share a specific interaction or experience with a researcher there that had an impact on you or your work?\u003C\/h2\u003E\u003Cp\u003EWorking with \u003Cstrong\u003EHamed\u003C\/strong\u003E \u003Cstrong\u003EOkhravi\u003C\/strong\u003E, a senior staff member at Lincoln Laboratory, was an amazing experience. He was my mentor and consistently went out of his way to connect me with people who could help me find datasets, access equipment, or get the lab space I needed for my work. For example, when I realized I needed a Faraday cage for my experiments, he connected me with the Mobile Device Lab and helped me get access very quickly. The lab manager was also immediately willing to let me use the space and equipment. That experience really reflected the culture I saw throughout Lincoln Laboratory. Everyone genuinely wanted to help each other get what they needed to move their research forward.\u003C\/p\u003E\u003Ch2\u003EHow did Georgia Tech prepare you for the work at Lincoln Laboratory, and did the internship change how you think about your research or future career?\u003C\/h2\u003E\u003Cp\u003EMy experience at Georgia Tech was instrumental in preparing me for my work at Lincoln Laboratory. The way I was taught to think through difficult research problems and work independently toward solutions translated well to a large research lab. I was able to hit the ground running and take ownership of a project because Georgia Tech had prepared me to lead research independently. The internship also gave me valuable experience in a research environment outside academia, which broadened my perspective on how I could pursue research in the future.\u003C\/p\u003E\u003Ch2\u003EYou\u2019ve said you want to work through the cybersecurity problems mariners have shared with you \u201cone by one.\u201d Which problem do you most want to tackle next, and why?\u003C\/h2\u003E\u003Cp\u003ENext, I\u2019d love to look at Starlink connectivity for ships or for autonomous shipping. Mariners we\u2019ve spoken with have raised concerns about both. With Starlink and increasingly autonomous vessels, they worry that greater remote connectivity could give attackers new ways to access onboard systems and disrupt ship operations. I think those concerns are worth investigating.\u003C\/p\u003E\u003Cp\u003EWe recently had a paper accepted at CCS that examines exposed solar distributed energy resources, and I think applying a similar perspective to exposed maritime equipment could be very interesting. That paper is available \u003Ca href=\u0022https:\/\/arxiv.org\/pdf\/2609.07783v1\u0022\u003Ehere\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003EWe also recently had a paper on measuring GPS spoofing of ships accepted at IEEE S\u0026amp;P. The full paper isn\u2019t online yet, but the project was directly motivated by mariners telling us that they were struggling with GPS spoofing. That made me want to find a way to systematically measure where spoofing was occurring.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EUltimately, the goal is to turn that kind of research into something useful for mariners, such as warning them when they are entering an area experiencing spoofing or when their own vessel may be affected and they should no longer trust their GPS. That is the kind of research I\u2019d like to continue doing: listening to the problems mariners are actually experiencing and finding ways to investigate and address them.\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EPhotos by Kevin Beasley and Terence Rushin\/College of Computing\u003C\/em\u003E\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EAnna Raymaker\u2019s maritime cybersecurity research is advancing through controlled AIS testing and collaboration with mariners. Her summer at MIT Lincoln Laboratory expanded both her methods and future research direction. \u2022 She built a safe AIS testbed using a Faraday cage, simulated GPS signals, and specialized hardware to study ship equipment without affecting real maritime traffic. \u2022 Raymaker plans to investigate Starlink connectivity, autonomous vessels, exposed maritime equipment, and GPS spoofing, with the goal of developing practical warnings for mariners.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Anna Raymaker\u2019s maritime cybersecurity research is advancing through controlled AIS testing and collaboration with mariners."}],"uid":"36253","created_gmt":"2026-09-29 18:46:36","changed_gmt":"2026-09-29 18:55:53","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-09-29T00:00:00-04:00","iso_date":"2026-09-29T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681294":{"id":"681294","type":"image","title":"Anna-Raymaker-3.jpg","body":null,"created":"1790707760","gmt_created":"2026-09-29 18:49:20","changed":"1790707760","gmt_changed":"2026-09-29 18:49:20","alt":"Smiling woman sitting in front of a window. Behind her buildings of Midtown Atlanta are visible. ","file":{"fid":"265665","name":"Anna-Raymaker-3.jpg","image_path":"\/sites\/default\/files\/2026\/09\/29\/Anna-Raymaker-3.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/29\/Anna-Raymaker-3.jpg","mime":"image\/jpeg","size":1969103,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/29\/Anna-Raymaker-3.jpg?itok=tvfoOWJN"}},"681295":{"id":"681295","type":"image","title":"Saman-Zonouz-Lab_86A4415.jpg","body":null,"created":"1790707976","gmt_created":"2026-09-29 18:52:56","changed":"1790707976","gmt_changed":"2026-09-29 18:52:56","alt":"A woman working on a simulated ship","file":{"fid":"265666","name":"Saman-Zonouz-Lab_86A4415.jpg","image_path":"\/sites\/default\/files\/2026\/09\/29\/Saman-Zonouz-Lab_86A4415.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/29\/Saman-Zonouz-Lab_86A4415.jpg","mime":"image\/jpeg","size":28896742,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/29\/Saman-Zonouz-Lab_86A4415.jpg?itok=ED3WU7x_"}},"681296":{"id":"681296","type":"image","title":"Saman-Zonouz-Lab_86A4427.jpg","body":null,"created":"1790707976","gmt_created":"2026-09-29 18:52:56","changed":"1790707976","gmt_changed":"2026-09-29 18:52:56","alt":"Three people working on a simulated ship in a lab","file":{"fid":"265667","name":"Saman-Zonouz-Lab_86A4427.jpg","image_path":"\/sites\/default\/files\/2026\/09\/29\/Saman-Zonouz-Lab_86A4427.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/29\/Saman-Zonouz-Lab_86A4427.jpg","mime":"image\/jpeg","size":29768827,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/29\/Saman-Zonouz-Lab_86A4427.jpg?itok=KWHcK2MP"}}},"media_ids":["681294","681295","681296"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"660406","name":"School of Cybersecurity \u0026 Privacy"},{"id":"660367","name":"School of Cybersecurity and Privacy"}],"categories":[{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"145","name":"Engineering"},{"id":"135","name":"Research"},{"id":"8862","name":"Student Research"}],"keywords":[],"core_research_areas":[{"id":"145171","name":"Cybersecurity"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJohn Popham\u003C\/p\u003E\u003Cp\u003ECommunications Officer for the School of Cybersecurity and Privacy\u003C\/p\u003E","format":"limited_html"}],"email":["jpopham3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}},"691627":{"#nid":"691627","#data":{"type":"news","title":"New Model Teaches Workplace AI to Read More Like Humans","body":[{"value":"\u003Cp\u003EModern artificial intelligence (AI) platforms can summarize reports, analyze documents, and answer questions in seconds. But when information is spread across dozens of slides, charts, and tables, even advanced models can miss important details.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAs many organizations and businesses are turning to AI to improve workplace efficiency, risk remains high. Between overlooked footnotes and misread graphics, small mistakes can have expensive consequences.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo address this challenge, researchers from Georgia Tech and J.P. Morgan developed SlideAgent. The new framework helps large language models (LLMs) better understand complex visual documents like presentation slide decks, brochures, and reports.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/arxiv.org\/abs\/2510.26615\u0022\u003ESlideAgent\u003C\/a\u003E works by breaking documents into multiple levels, allowing the model to analyze both the big picture and the fine details. This human-inspired approach leads to more accurate and reliable interpretation than existing systems.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EBeyond improving workplace tools, SlideAgent also points to a broader shift in AI. Instead of building only larger and more powerful models, the work shows how smarter design and more efficient reasoning can improve performance.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cMultimodal LLMs such as GPT, Gemini, and Claude, can save people time and reduce the mental effort required to understand these documents, but they remain imperfect,\u201d said \u003Ca href=\u0022https:\/\/ahren09.github.io\/\u0022\u003EYiqiao (Ahren) Jin\u003C\/a\u003E, a Ph.D. candidate in Georgia Tech\u2019s \u003Ca href=\u0022https:\/\/cse.gatech.edu\/\u0022\u003ESchool of Computational Science and Engineering\u003C\/a\u003E (CSE).\u003C\/p\u003E\u003Cp\u003E\u201cIn high-stakes fields such as finance, for example, misreading a number, overlooking a footnote, or making an incorrect comparison across pages could affect reporting, risk assessment, or strategic decisions.\u201d\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe researchers tested SlideAgent on a wide range of real-world documents, including financial presentations, technical slides, and visual question-answering datasets.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe system consistently outperformed leading commercial models and open-source tools throughout the evaluation. In some cases, it improved accuracy by up to 10%. The gains were especially strong on more complex tasks, such as comparing information across slides or understanding how visuals relate to each other on a page.\u003C\/p\u003E\u003Cp\u003E\u201cWe found the results very encouraging. SlideAgent reaches an improvement of 7.9% over its proprietary base model and 9.8% over the evaluated open-source base models,\u201d said Jin, the project\u2019s lead researcher.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cThese are meaningful gains given the strength of the underlying multimodal models and the difficulty of the tasks.\u201d\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ECurrent multimodal AI systems often process entire pages at once. This approach can lead to mistakes, such as miscounting items in a chart or overlooking important details in dense visuals.\u003C\/p\u003E\u003Cp\u003ESlideAgent addresses this by mimicking how people read documents. Instead of treating each page as a single unit, the system looks at information at three levels: the full document, individual pages, and specific elements like charts, tables, and text blocks.\u003C\/p\u003E\u003Cp\u003EA network of agents, each specialized for a specific level, divides and coordinates analysis. Then, SlideAgent combines outputs to build a structured understanding of the overall document. This allows it to answer questions more accurately and reason across multiple pages.\u003C\/p\u003E\u003Cp\u003E\u201cThe central inspiration was how people naturally read a long presentation,\u201d Jin said.\u003C\/p\u003E\u003Cp\u003E\u201cWe first develop an understanding of the overall narrative, then identify the relevant pages or sections, and finally zoom in on individual charts, tables, or text blocks when precise evidence is needed.\u201d\u003C\/p\u003E\u003Cp\u003EThe work highlights a growing challenge with AI. As systems become more popular and more powerful, users increasingly discover the technology\u2019s limitations. This is especially true for real-world tasks that require structured reasoning and contextual understanding.\u003C\/p\u003E\u003Cp\u003ESlideAgent shows that better performance does not always come from building bigger models. Instead, it points to smarter ways of organizing how AI processes information that can lead to improvement.\u003C\/p\u003E\u003Cp\u003EThe Association for Computational Linguistics (ACL) accepted SlideAgent for presentation at its annual meeting. The 64th \u003Ca href=\u0022https:\/\/2026.aclweb.org\/\u0022\u003EACL 2026 meeting\u003C\/a\u003E took place July 2-7 in San Diego.\u003C\/p\u003E\u003Cp\u003EACL is a scientific and professional organization for researchers in natural language processing (NLP). Its namesake conference is one of the world\u2019s leading venues for presenting NLP research.\u003C\/p\u003E\u003Cp\u003EACL 2026 followed a year after Jin completed an internship at J.P. Morgan AI Research, where he worked on SlideAgent. He interned under \u003Cstrong\u003ERachneet Kaur\u003C\/strong\u003E, \u003Cstrong\u003EZhen Zeng\u003C\/strong\u003E, and \u003Cstrong\u003ESumitra Ganesh\u003C\/strong\u003E, all co-authors of the paper. School of CSE Associate Professor \u003Ca href=\u0022https:\/\/faculty.cc.gatech.edu\/~srijan\/\u0022\u003ESrijan Kumar\u003C\/a\u003E advises Jin at Georgia Tech.\u003C\/p\u003E\u003Cp\u003EAlong with SlideAgent, Jin authored two other papers accepted at ACL 2026.\u003C\/p\u003E\u003Cp\u003E\u201cConferences such as ACL are valuable not only for sharing results, but also for refining future project ideas with the broader community. Discussions across institutions and research areas can reveal limitations, suggest new evaluations, and spark collaborations that are difficult to develop in isolation,\u201d Jin said.\u003C\/p\u003E\u003Cp\u003E\u201cFor SlideAgent, I was particularly interested in feedback on how we can make the framework more computationally efficient without sacrificing accuracy or interpretability.\u201d\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EModern artificial intelligence (AI) platforms can summarize reports, analyze documents, and answer questions in seconds. But when information is spread across dozens of slides, charts, and tables, even advanced models can miss important details.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EAs many organizations and businesses are turning to AI to improve workplace efficiency, risk remains high. Between overlooked footnotes and misread graphics, small mistakes can have expensive consequences.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ETo address this challenge, researchers from Georgia Tech and J.P. Morgan developed SlideAgent. The new framework helps large language models (LLMs) better understand complex visual documents like presentation slide decks, brochures, and reports.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ESlideAgent works by breaking documents into multiple levels, allowing the model to analyze both the big picture and the fine details. This human-inspired approach leads to more accurate and reliable interpretation than existing systems.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EBeyond improving workplace tools, SlideAgent also points to a broader shift in AI. Instead of building only larger and more powerful models, the work shows how smarter design and more efficient reasoning can improve performance.\u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"The new AI framework called SlideAgent helps large language models (LLMs) better understand complex visual documents used in the workplace like presentation slide decks, brochures, and reports. "}],"uid":"36319","created_gmt":"2026-08-12 12:01:25","changed_gmt":"2026-09-29 18:42:26","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-08-12T00:00:00-04:00","iso_date":"2026-08-12T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"680843":{"id":"680843","type":"image","title":"SlideAgent-Head-Image.jpg","body":null,"created":"1786536102","gmt_created":"2026-08-12 12:01:42","changed":"1786536102","gmt_changed":"2026-08-12 12:01:42","alt":"Yiqiao (Ahren) Jin ACL 2026","file":{"fid":"265169","name":"SlideAgent-Head-Image.jpg","image_path":"\/sites\/default\/files\/2026\/08\/12\/SlideAgent-Head-Image.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/08\/12\/SlideAgent-Head-Image.jpg","mime":"image\/jpeg","size":96345,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/08\/12\/SlideAgent-Head-Image.jpg?itok=MXXpRJcQ"}},"680844":{"id":"680844","type":"image","title":"YJ_ACL2026.jpg","body":null,"created":"1786536492","gmt_created":"2026-08-12 12:08:12","changed":"1786536492","gmt_changed":"2026-08-12 12:08:12","alt":"Yiqiao (Ahren) Jin ACL 2026","file":{"fid":"265170","name":"YJ_ACL2026.jpg","image_path":"\/sites\/default\/files\/2026\/08\/12\/YJ_ACL2026.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/08\/12\/YJ_ACL2026.jpg","mime":"image\/jpeg","size":48282,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/08\/12\/YJ_ACL2026.jpg?itok=Vns4uEGI"}},"680845":{"id":"680845","type":"image","title":"YJ_ACL2026.jpeg","body":null,"created":"1786536520","gmt_created":"2026-08-12 12:08:40","changed":"1786536520","gmt_changed":"2026-08-12 12:08:40","alt":"Yiqiao (Ahren) Jin ACL 2026","file":{"fid":"265171","name":"YJ_ACL2026.jpeg","image_path":"\/sites\/default\/files\/2026\/08\/12\/YJ_ACL2026.jpeg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/08\/12\/YJ_ACL2026.jpeg","mime":"image\/jpeg","size":219002,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/08\/12\/YJ_ACL2026.jpeg?itok=inGoNwsP"}}},"media_ids":["680843","680844","680845"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[{"id":"194606","name":"Artificial Intelligence"},{"id":"139","name":"Business"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"194609","name":"Industry"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[{"id":"654","name":"College of Computing"},{"id":"166983","name":"School of Computational Science and Engineering"},{"id":"187915","name":"go-researchnews"},{"id":"9153","name":"Research Horizons"},{"id":"10199","name":"Daily Digest"},{"id":"181991","name":"Georgia Tech News Center"},{"id":"170447","name":"Institute for Data Engineering and Science"},{"id":"176858","name":"machine learning center"},{"id":"9167","name":"machine learning"},{"id":"187812","name":"artificial intelligence (AI)"},{"id":"14646","name":"human-computer interaction"},{"id":"192863","name":"go-ai"},{"id":"194384","name":"Tech AI"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"39431","name":"Data Engineering and Science"}],"news_room_topics":[{"id":"71881","name":"Science and Technology"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBryant Wine, Communications Officer\u003Cbr\u003E\u003Ca href=\u0022mailto:bryant.wine@cc.gatech.edu\u0022\u003Ebryant.wine@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}},"692643":{"#nid":"692643","#data":{"type":"news","title":"Internship Highlights Industry\u2019s Role in Advancing Safe, Trustworthy AI","body":[{"value":"\u003Cp\u003EAcademic researchers often focus on advancing fundamental knowledge, while industry puts that knowledge into practice. This summer, Ph.D. student\u0026nbsp;\u003Ca href=\u0022https:\/\/mphute.github.io\/\u0022\u003EMansi Phute\u003C\/a\u003E experienced both sides of the process during an internship focused on making artificial intelligence (AI) safe, trustworthy, and reliable.\u003C\/p\u003E\u003Cp\u003EUpon returning to Georgia Tech, Phute reflected on her summer internship and what it taught her about the evolving relationship between research and industry.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EStudent:\u003C\/strong\u003E Mansi Phute\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EResearch Interests:\u003C\/strong\u003E Machine learning (ML) robustness and artificial intelligence (AI) safety\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDegree Program:\u003C\/strong\u003E Ph.D. in Computer Science\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EFaculty Advisor\u003C\/strong\u003E: School of CSE Professor and Associate Chair\u0026nbsp;\u003Ca href=\u0022https:\/\/poloclub.github.io\/polochau\/\u0022\u003EPolo Chau\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003E2026 Internship\u003C\/strong\u003E: International Business Machines (\u003Ca href=\u0022https:\/\/www.ibm.com\/us-en\u0022\u003EIBM\u003C\/a\u003E), San Jose, California\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EWhat about IBM interested you in applying for and accepting an internship there?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EIBM is often at the forefront of AI safety, my field of interest, and has a culture that encourages exploratory and fundamental research. I felt this would give me a closer look at cutting-edge industry approaches without compromising on my research interests or my progress toward my thesis.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EHow well did your coursework and experience at Georgia Tech prepare you for your IBM internship?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EMy experience at Georgia Tech was very helpful in preparing me for IBM. My coursework and other academic experiences certainly transferred over, but I believe that the wide range of people I met during those courses and what I learned from them helped me connect and relate strongly with people at IBM. Being conversant in different fields of research really helped me interact better with IBM coworkers and feel comfortable in a new environment.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EWhat did you work on while interning at IBM?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EI worked on IBM\u2019s AI Foundations team, focusing on the security of multimodal agent communication during my internship. This is an important problem as we see an increase in agents applied in many use cases. It was also closely aligned with my research interests of AI safety.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDo you have a favorite memory or remarkable achievement from your internship?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EOne of my favorite moments was presenting my work to a broad, cross-team audience of technical and non-technical members. Afterward, my manager told me I was good at explaining my research to people with varying levels of familiarity with the domain. This feedback meant a lot to me because communicating clearly across different audiences is a skill I\u0027ve deliberately worked to improve. So, hearing that the effort was paying off was very rewarding.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EOverall, how helpful was this internship toward your studies at Georgia Tech and your career as an aspiring researcher?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EThis internship was very valuable for my development as an aspiring researcher. I worked alongside accomplished people in the AI safety field on projects that aligned closely with my research interests. I also saw how those same projects connect to a company\u0027s broader business priorities, a perspective that isn\u2019t easily available in academic settings. I shared many fruitful discussions with people working in safety, policy, and alignment, which gave me a much clearer sense of how industry approaches these issues compared to the more academic-oriented framing I am used to.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBased on what you learned during your internship, how important is private industry in progressing research and scientific discovery?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EWorking in private industry was a fascinating experience. I come away believing that industry plays an important role in advancing research, especially in AI, where companies have access to computing resources that are less prohibitive than in academic environments. I also think that because private industry has a strong hand in implementing and deploying research,\u0026nbsp;understanding industry priorities can help us frame and design our research in ways that complement industry applications. This ensures research has a bigger impact, particularly in the domain of ML safety and reliability.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EAcademic researchers often focus on advancing fundamental knowledge, while industry puts that knowledge into practice. This summer, Ph.D. student\u0026nbsp;\u003Ca href=\u0022https:\/\/mphute.github.io\/\u0022\u003EMansi Phute\u003C\/a\u003E experienced both sides of the process during an internship focused on making artificial intelligence (AI) safe, trustworthy, and reliable.\u003C\/p\u003E\u003Cp\u003EUpon returning to Georgia Tech, Phute reflected on her summer internship and what it taught her about the evolving relationship between research and industry.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Ph.D. student Mansi Phute spent this summer at an internship focused on making artificial intelligence (AI) safe, trustworthy, and reliable."}],"uid":"36319","created_gmt":"2026-09-17 15:48:44","changed_gmt":"2026-09-21 14:49:44","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-09-17T00:00:00-04:00","iso_date":"2026-09-17T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681184":{"id":"681184","type":"image","title":"MP-Head-Image.jpg","body":null,"created":"1789660134","gmt_created":"2026-09-17 15:48:54","changed":"1789660134","gmt_changed":"2026-09-17 15:48:54","alt":"CSE Mansi Phute","file":{"fid":"265549","name":"MP-Head-Image.jpg","image_path":"\/sites\/default\/files\/2026\/09\/17\/MP-Head-Image.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/17\/MP-Head-Image.jpg","mime":"image\/jpeg","size":139529,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/17\/MP-Head-Image.jpg?itok=ip-e5Jk6"}},"681185":{"id":"681185","type":"image","title":"MP-IBM-Internship.jpg","body":null,"created":"1789660171","gmt_created":"2026-09-17 15:49:31","changed":"1789660171","gmt_changed":"2026-09-17 15:49:31","alt":"CSE Mansi Phute","file":{"fid":"265550","name":"MP-IBM-Internship.jpg","image_path":"\/sites\/default\/files\/2026\/09\/17\/MP-IBM-Internship.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/17\/MP-IBM-Internship.jpg","mime":"image\/jpeg","size":208527,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/17\/MP-IBM-Internship.jpg?itok=IniBDOHb"}}},"media_ids":["681184","681185"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[{"id":"194606","name":"Artificial Intelligence"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"194609","name":"Industry"},{"id":"135","name":"Research"},{"id":"8862","name":"Student Research"},{"id":"194612","name":"Workforce Development"}],"keywords":[{"id":"654","name":"College of Computing"},{"id":"166983","name":"School of Computational Science and Engineering"},{"id":"9153","name":"Research Horizons"},{"id":"187915","name":"go-researchnews"},{"id":"170447","name":"Institute for Data Engineering and Science"},{"id":"192863","name":"go-ai"},{"id":"194384","name":"Tech AI"},{"id":"187812","name":"artificial intelligence (AI)"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"39431","name":"Data Engineering and Science"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBryant Wine, Communications Officer\u003Cbr\u003E\u003Ca href=\u0022mailto:bryant.wine@cc.gatech.edu\u0022\u003Ebryant.wine@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}},"692727":{"#nid":"692727","#data":{"type":"news","title":"Internship Explores Government\u2019s Investment for the Future","body":[{"value":"\u003Cp\u003EMany scientific breakthroughs begin with long-term research investments. Government agencies often play a central role in this process, supporting work that addresses national priorities while laying the foundation for future innovations.\u003C\/p\u003E\u003Cp\u003EThis summer, M.S. student \u003Ca href=\u0022https:\/\/www.linkedin.com\/in\/joey-cuthbert\/\u0022\u003EJoey Cuthbert\u003C\/a\u003E contributed to this mission through an internship at the Air Force Research Laboratory (AFRL). Upon returning to campus, Cuthbert reflected on his internship and what he learned working alongside researchers in government and the defense community. \u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EStudent:\u003C\/strong\u003E Joey Cuthbert\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EResearch Interests:\u003C\/strong\u003E Machine learning (ML), model-based systems engineering\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDegree Program:\u003C\/strong\u003E M.S. in Computational Science and Engineering, home unit in \u003Ca href=\u0022https:\/\/www.isye.gatech.edu\/\u0022\u003EH. Milton Stewart School of Industrial and Systems Engineering\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003E2026 Internship\u003C\/strong\u003E: Sensors Directorate Internship Program with Air Force Research Laboratory (\u003Ca href=\u0022https:\/\/www.afrl.af.mil\/\u0022\u003EAFRL\u003C\/a\u003E) and the National Air and Space Intelligence Center (\u003Ca href=\u0022https:\/\/www.nasic.af.mil\/\u0022\u003ENASIC\u003C\/a\u003E), Beavercreek, Ohio\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EWhat about AFRL interested you in applying for and accepting an internship there?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EThe Sensors Directorate Internship Program (SDIP) provided a unique opportunity to work alongside mentors from AFRL and NASIC on a defense-related research project over a 14-week internship. This aligned with my desire to work on applied ML research in the defense sector and allowed me to better understand the ins and outs of government and government-contracting work. The program provided competitive pay and housing throughout the program, which was a huge plus for me.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EHow well did your coursework and experience at Georgia Tech prepare you for your AFRL internship?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EMy experience and coursework at Georgia Tech helped me a great deal this summer. I believe my understanding of ML has greatly improved over the past two semesters, which helped me complete my internship project. All of my experiments ran on high-performance computing (HPC) systems, and I felt I had a head start since I completed an HPC class last spring.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EWhat did you work on while interning at AFRL?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EI worked on an image-classification robustness project for convolutional neural networks (CNNs) using synthetic aperture radar (SAR) data. I built a robustness benchmark by testing a model against nine types of noise, and used it to show how we can effectively increase robustness by inducing shape-bias in the model during training.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDo you have a favorite memory or remarkable achievement from your internship?\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDuring the summer, we went on a tour of nearby \u003Ca href=\u0022https:\/\/www.wpafb.af.mil\/\u0022\u003EWright-Patterson Air Force Base\u003C\/a\u003E, where we visited the sensors directorate buildings and checked out some of their labs. I also received the best poster presentation award among approximately 40 interns.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EOverall, how helpful was this internship toward your studies at Georgia Tech and career as an aspiring researcher?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EThis program provided great strides toward my research career goals. My coursework has provided a great foundation in ML, and I was able to apply this knowledge to a project. The internship offered me lots of autonomy, as well as time to explore different paths to find results.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EFrom what you learned on your internship, how important are government agencies in progressing research and scientific discovery?\u003C\/strong\u003E\u003Cbr\u003E\u003Cbr\u003EI believe government agencies are massively valuable in advancing research and scientific discovery, especially within the defense sector. All work at AFRL has the goal of giving warfighters the greatest advantage possible. This often entails looking 10 to 20 years into the future of science and technology and trying to get there as fast as possible.\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EMany scientific breakthroughs begin with long-term research investments. Government agencies often play a central role in this process, supporting work that addresses national priorities while laying the foundation for future innovations.\u003C\/p\u003E\u003Cp\u003EThis summer, M.S. student Joey Cuthbert contributed to this mission through an internship at the Air Force Research Laboratory (AFRL). Upon returning to campus, Cuthbert reflected on his internship and what he learned working alongside researchers in government and the defense community. \u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"This summer, M.S. student Joey Cuthbert completed an internship at the Air Force Research Laboratory (AFRL), supporting work that addresses national priorities while laying the foundation for future innovations."}],"uid":"36319","created_gmt":"2026-09-21 14:42:15","changed_gmt":"2026-09-21 14:48:56","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-09-21T00:00:00-04:00","iso_date":"2026-09-21T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681208":{"id":"681208","type":"image","title":"JC-Head-Image.jpg","body":null,"created":"1790001748","gmt_created":"2026-09-21 14:42:28","changed":"1790001748","gmt_changed":"2026-09-21 14:42:28","alt":"CSE Joey Cuthbert","file":{"fid":"265574","name":"JC-Head-Image.jpg","image_path":"\/sites\/default\/files\/2026\/09\/21\/JC-Head-Image.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/21\/JC-Head-Image.jpg","mime":"image\/jpeg","size":99824,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/21\/JC-Head-Image.jpg?itok=pWBltqhA"}},"681209":{"id":"681209","type":"image","title":"SARdust-Poster.jpg","body":null,"created":"1790001781","gmt_created":"2026-09-21 14:43:01","changed":"1790001781","gmt_changed":"2026-09-21 14:43:01","alt":"CSE Joey Cuthbert Poster","file":{"fid":"265575","name":"SARdust-Poster.jpg","image_path":"\/sites\/default\/files\/2026\/09\/21\/SARdust-Poster.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/21\/SARdust-Poster.jpg","mime":"image\/jpeg","size":401402,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/21\/SARdust-Poster.jpg?itok=QqefVp7Y"}}},"media_ids":["681208","681209"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[{"id":"136","name":"Aerospace"},{"id":"194606","name":"Artificial Intelligence"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"147","name":"Military Technology"},{"id":"194610","name":"National Interests\/National Security"},{"id":"135","name":"Research"},{"id":"193157","name":"Student Honors and Achievements"},{"id":"8862","name":"Student Research"}],"keywords":[{"id":"654","name":"College of Computing"},{"id":"166983","name":"School of Computational Science and Engineering"},{"id":"594","name":"college of engineering"},{"id":"180027","name":". ISyE"},{"id":"2633","name":"Air Force"},{"id":"191204","name":"Air Force Research Laboratory"},{"id":"1325","name":"aerospace"},{"id":"9167","name":"machine learning"},{"id":"187812","name":"artificial intelligence (AI)"},{"id":"9153","name":"Research Horizons"},{"id":"187915","name":"go-researchnews"},{"id":"192863","name":"go-ai"},{"id":"10199","name":"Daily Digest"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"39431","name":"Data Engineering and Science"},{"id":"39481","name":"National Security"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBryant Wine, Communications Officer\u003Cbr\u003E\u003Ca href=\u0022mailto:bryant.wine@cc.gatech.edu\u0022\u003Ebryant.wine@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}},"692596":{"#nid":"692596","#data":{"type":"news","title":"Internship Connects Supercomputing with National Priorities","body":[{"value":"\u003Cp\u003ENational laboratories play a critical role in advancing science, developing energy technologies, and ensuring national security. This summer, Ph.D. student \u003Ca href=\u0022https:\/\/www.linkedin.com\/in\/tage-burnett-537549221\/\u0022\u003ETage Burnett\u003C\/a\u003E contributed to that mission firsthand during an internship at Oak Ridge National Laboratory (ORNL) in Tennessee.\u003C\/p\u003E\u003Cp\u003EThe internship provided Burnett with valuable insight into national laboratory research and reinforced skills he developed through his studies at Georgia Tech. When he returned to campus, we asked Burnett to share more about his internship and what he learned.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EStudent:\u003C\/strong\u003E Tage Burnett\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EResearch Interests:\u003C\/strong\u003E Fusion energy, computational plasma physics, high-performance computing, and structure-preserving machine learning\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDegree Program:\u003C\/strong\u003E Ph.D. in Computational Science and Engineering\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EFaculty Advisor\u003C\/strong\u003E: School of CSE Assistant Professor \u003Ca href=\u0022https:\/\/tangqi.github.io\/\u0022\u003EQi Tang\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003E2026 Internship\u003C\/strong\u003E: Oak Ridge National Laboratory, Oak Ridge, Tennessee\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EMany people are unfamiliar with national laboratories, like ORNL. Could you explain the purpose of these institutions and why they are important?\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EThe Department of Energy (DOE) national laboratories are responsible for moving forward science and technology in the United States and solving high-consequence challenges in science, energy, and national security. They work on both applied and theoretical research with both short-term and long-term returns. ORNL has eight core research areas: biology and environment, energy science, fusion and fission, isotopes, physical sciences, national security, neutron science, and supercomputing. I was an intern in the supercomputing division.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EHow well did coursework and experience at Georgia Tech prepare you for your ORNL internship?\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EMy coursework at Georgia Tech was vital in my preparation for this internship. I wrote highly parallel code where I leaned heavily on what I learned in \u003Cem\u003ECSE 6220: High-Performance Computing\u003C\/em\u003E. I also worked on numerical methods which required an understanding of partial differential equations and numerical linear algebra which I also learned at Georgia Tech from classes like \u003Cem\u003ECSE 6643: Numerical Linear Algebra\u003C\/em\u003E and a space plasma physics course.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EWhat did you work on while interning at ORNL?\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EAt ORNL, I was a developer on the Adaptive Sparse Grid Discretization (\u003Ca href=\u0022https:\/\/joss.theoj.org\/papers\/10.21105\/joss.06766\u0022\u003EASGarD\u003C\/a\u003E) codebase. The code uses adaptive sparse grids and the Discontinuous Galerkin method to beat the curse of dimensionality and solve high-dimensional partial differential equations (PDEs). \u003Ca href=\u0022https:\/\/github.com\/openjournals\/joss-reviews\/issues\/6766\u0022\u003EThe code\u003C\/a\u003E is designed to simulate fully kinetic plasmas in up to 6-dimensional phase space. My project was to implement an iterative method to solve the efficiently solve the Poisson equation within the codebase. This project gave me hands on experience with linear algebra, numerical PDEs, parallel computing and software engineering which was invaluable to my development as a CSE researcher.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDo you have a favorite memory or remarkable achievement from your internship?\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EMy favorite memory from my internship was spending time with the other ORNL interns outside of work. There was an amazing group of interns at ORNL, and it was great getting to know them. One particularly good memory was when we went out to a restaurant with live music and played laser tag during our last week of the internship to celebrate our time at ORNL. The achievement I am most proud of was getting a working, highly efficient version of the Poisson solver into ASGarD. The ASGarD codebase is open source, so I hope other plasma physics researchers will use the code and find it helpful for their research.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EWhile interning, you were selected for a GEM Fellowship, which Georgia Tech and ORNL nominated you for. What does this fellowship mean to you and is there anything you would like to say to your supporters?\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ETo me, receiving the \u003Ca href=\u0022https:\/\/www.gemfellowship.org\/gem-fellowship-program\/#a\u0022\u003EGEM Fellowship\u003C\/a\u003E indicates that other people recognize the hard work I am doing, and they believe in my ability to meaningfully contribute to the field. Having this support from GEM, ORNL, and Georgia Tech gives me greater confidence in myself and my potential and inspires me to put my all into my work. I would like all my supporters to know that I am so grateful for the opportunity you have given me to be a part of the excellent community of researchers within GEM, ORNL, and Georgia Tech. I will do my very best to make your support worthwhile!\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EOverall, how helpful was this internship toward your studies at Georgia Tech and career as an aspiring researcher?\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EThe internship was extremely important to both my studies at Georgia Tech and my career as a researcher. The hands-on experience I gained is irreplaceable and it helped me to apply all the skills I have developed throughout my education. I am also optimistic that the internship will open doors for me when I am seeking a job post-graduation.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ENational laboratories play a critical role in advancing science, developing energy technologies, and ensuring national security. This summer, Ph.D. student \u003Cstrong\u003ETage Burnett\u003C\/strong\u003E contributed to that mission firsthand during an internship at Oak Ridge National Laboratory (ORNL) in Tennessee.\u003C\/p\u003E\u003Cp\u003EThe internship provided Burnett valuable insight into national laboratory research and reinforced skills he developed through his studies at Georgia Tech. When he returned to campus, we asked Burnett to share more about his internship and what he learned.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"National laboratories play a critical role in advancing science, developing energy technologies, and ensuring national security. This summer, Ph.D. student Tage Burnett contributed to that mission firsthand during an internship at ORNL."}],"uid":"36319","created_gmt":"2026-09-15 16:02:56","changed_gmt":"2026-09-21 14:48:37","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-09-15T00:00:00-04:00","iso_date":"2026-09-15T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681151":{"id":"681151","type":"image","title":"Tage-Burnett-Head-Image.jpg","body":null,"created":"1789488262","gmt_created":"2026-09-15 16:04:22","changed":"1789488262","gmt_changed":"2026-09-15 16:04:22","alt":"CSE Tage Burnett","file":{"fid":"265514","name":"Tage-Burnett-Head-Image.jpg","image_path":"\/sites\/default\/files\/2026\/09\/15\/Tage-Burnett-Head-Image.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/15\/Tage-Burnett-Head-Image.jpg","mime":"image\/jpeg","size":117243,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/15\/Tage-Burnett-Head-Image.jpg?itok=L5ERGUNS"}},"681153":{"id":"681153","type":"image","title":"TB-ORNL-Mentor.jpeg","body":null,"created":"1789488297","gmt_created":"2026-09-15 16:04:57","changed":"1789488297","gmt_changed":"2026-09-15 16:04:57","alt":"CSE Tage Burnett","file":{"fid":"265515","name":"TB-ORNL-Mentor.jpeg","image_path":"\/sites\/default\/files\/2026\/09\/15\/TB-ORNL-Mentor.jpeg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/15\/TB-ORNL-Mentor.jpeg","mime":"image\/jpeg","size":93096,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/15\/TB-ORNL-Mentor.jpeg?itok=9neLNYx7"}}},"media_ids":["681151","681153"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"144","name":"Energy"},{"id":"135","name":"Research"},{"id":"193157","name":"Student Honors and Achievements"},{"id":"8862","name":"Student Research"},{"id":"194612","name":"Workforce Development"}],"keywords":[{"id":"654","name":"College of Computing"},{"id":"166983","name":"School of Computational Science and Engineering"},{"id":"187915","name":"go-researchnews"},{"id":"9153","name":"Research Horizons"},{"id":"170447","name":"Institute for Data Engineering and Science"},{"id":"108061","name":"Oak Ridge National Laboratory"},{"id":"663","name":"Department of Energy"},{"id":"167322","name":"supercomputing"}],"core_research_areas":[{"id":"39431","name":"Data Engineering and Science"},{"id":"39531","name":"Energy and Sustainable Infrastructure"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBryant Wine, Communications Officer\u003Cbr\u003E\u003Ca href=\u0022mailto:bryant.wine@cc.gatech.edu\u0022\u003Ebryant.wine@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}},"692299":{"#nid":"692299","#data":{"type":"news","title":"Georgia Tech Researchers Share AI Cyber Challenge Lessons at USENIX Security 2026","body":[{"value":"\u003Cp\u003EWhat can artificial intelligence (AI) do to protect software from cyberattacks?\u003C\/p\u003E\u003Cp\u003EGeorgia Tech researchers \u003Ca href=\u0022https:\/\/sites.gatech.edu\/winningaixcc\/\u0022\u003Espent two years\u003C\/a\u003E helping to answer that question through \u003Ca href=\u0022https:\/\/www.darpa.mil\/research\/programs\/ai-cyber\u0022\u003EDARPA\u2019s AI Cyber Challenge\u003C\/a\u003E (AIxCC), a competition designed to test whether AI could identify and fix security vulnerabilities in real-world software.\u003C\/p\u003E\u003Cp\u003ENow, they are sharing what they learned with the cybersecurity community.\u003C\/p\u003E\u003Cp\u003ETheir paper, \u003Ca href=\u0022https:\/\/www.usenix.org\/system\/files\/usenixsecurity26-zhang-cen.pdf\u0022\u003E\u003Cem\u003ESoK: DARPA\u2019s AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned\u003C\/em\u003E\u003C\/a\u003E, was presented at \u003Ca href=\u0022https:\/\/www.usenix.org\/conference\/usenixsecurity26\u0022\u003EUSENIX Security 2026,\u003C\/a\u003E one of the world\u0027s leading cybersecurity conferences. The paper was selected as a runner-up for the conference\u2019s distinguished paper award, placing it among 36 recognized papers from 362 accepted papers out of 3,028 submissions.\u003C\/p\u003E\u003Cp\u003EThe paper examines how the seven finalist teams approached the competition and what the results reveal about the future of AI-powered cybersecurity.\u003C\/p\u003E\u003Ch2\u003EPutting AI to the Test\u003C\/h2\u003E\u003Cp\u003EAIxCC challenged teams to build Cyber Reasoning Systems (CRSs) that could operate with minimal human assistance to identify software vulnerabilities, develop fixes, and determine whether security alerts were real threats.\u003C\/p\u003E\u003Cp\u003EThe teams had 143 hours to analyze 53 software projects during the final competition.\u003C\/p\u003E\u003Cp\u003EGeorgia Tech\u2019s \u003Ca href=\u0022https:\/\/team-atlanta.github.io\/\u0022\u003ETeam Atlanta\u003C\/a\u003E, which won the competition, used an approach that combined multiple AI agents with traditional security tools. Other teams used different approaches, including applying AI for specific tasks or building highly autonomous AI agents.\u003C\/p\u003E\u003Cp\u003EThe variety of systems provided researchers with a rare opportunity to compare different approaches to AI-powered cybersecurity.\u003C\/p\u003E\u003Ch2\u003ELesson from the Competition\u003C\/h2\u003E\u003Cp\u003EOne of the biggest lessons was that reliability matters as much as intelligence.\u003C\/p\u003E\u003Cp\u003ESome systems were highly capable but struggled to remain operational while analyzing large, complicated software projects. The strongest systems were often those that could work reliably throughout the competition.\u003C\/p\u003E\u003Cp\u003EThe researchers also found that AI and traditional security tools have different strengths. Traditional tools were still effective at finding common bugs, while AI performed better at reasoning through more complex problems.\u003C\/p\u003E\u003Cp\u003EHowever, AI-generated fixes remain a major challenge.\u003C\/p\u003E\u003Cp\u003EResearchers found that 38% to 46% of AI-generated patches were semantically incorrect. This means a patch might stop a security problem but also break a feature or create another problem.\u003C\/p\u003E\u003Cp\u003EThe results show that AI can play an important role in cybersecurity, but human experts are still needed to verify the safety of AI-generated fixes.\u003C\/p\u003E\u003Ch2\u003ESharing the Lessons\u003C\/h2\u003E\u003Cp\u003E\u003Cstrong\u003ECen\u003C\/strong\u003E \u003Cstrong\u003EZhang\u003C\/strong\u003E, the paper\u2019s first author, said the research offers a unique look at the competition by combining lessons from the finalist teams, organizers, and DARPA\u2019s data.\u003C\/p\u003E\u003Cp\u003E\u201cThis paper provides a unique angle on how AIxCC was designed, the techniques teams used, and what the scores reveal and conceal,\u201d Zhang said.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EJiho\u003C\/strong\u003E \u003Cstrong\u003EKim\u003C\/strong\u003E presented the paper at USENIX Security 2026. He said the presentation was an opportunity to share lessons from two years of work with the broader cybersecurity community.\u003C\/p\u003E\u003Cp\u003E\u201cSeeing the strong interest and thoughtful questions from the audience made the experience particularly rewarding,\u201d Kim said.\u003C\/p\u003E\u003Cp\u003EThe researchers say they hope the lessons from AIxCC will help guide the next generation of cybersecurity tools.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EWhat can artificial intelligence (AI) do to protect software from cyberattacks?\u003C\/p\u003E\u003Cp\u003EGeorgia Tech researchers spent two years helping to answer that question through DARPA\u2019s AI Cyber Challenge (AIxCC), a competition designed to test whether AI could identify and fix security vulnerabilities in real-world software.\u003C\/p\u003E\u003Cp\u003ENow, they are sharing what they learned with the cybersecurity community.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Georgia Tech researchers spent two years helping to answer the question: What can artificial intelligence (AI) do to protect software from cyberattacks?"}],"uid":"36253","created_gmt":"2026-09-03 19:03:58","changed_gmt":"2026-09-03 19:20:31","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-09-03T00:00:00-04:00","iso_date":"2026-09-03T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"681067":{"id":"681067","type":"image","title":"USENIX-AIxCC-Paper-web-copy.jpg","body":null,"created":"1788463126","gmt_created":"2026-09-03 19:18:46","changed":"1788463126","gmt_changed":"2026-09-03 19:18:46","alt":"A dark room with a man presenting from a slideshow","file":{"fid":"265418","name":"USENIX-AIxCC-Paper-web-copy.jpg","image_path":"\/sites\/default\/files\/2026\/09\/03\/USENIX-AIxCC-Paper-web-copy.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/09\/03\/USENIX-AIxCC-Paper-web-copy.jpg","mime":"image\/jpeg","size":1074015,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/09\/03\/USENIX-AIxCC-Paper-web-copy.jpg?itok=473Fyfwp"}}},"media_ids":["681067"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"660406","name":"School of Cybersecurity \u0026 Privacy"},{"id":"660367","name":"School of Cybersecurity and Privacy"}],"categories":[{"id":"194606","name":"Artificial Intelligence"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"193158","name":"Student Competition Winners (academic, innovation, and research)"},{"id":"8862","name":"Student Research"}],"keywords":[],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"145171","name":"Cybersecurity"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJohn Popham\u003C\/p\u003E\u003Cp\u003ECommunications Officer for the School of Cybersecurity and Privacy\u003C\/p\u003E","format":"limited_html"}],"email":["jpopham3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}},"691762":{"#nid":"691762","#data":{"type":"news","title":"EPIcenter Summer Research Program Helps Doctoral Students Advance Energy Research ","body":[{"value":"\u003Cp\u003EFour Georgia Tech doctoral students spent the summer working on their dissertation research through the Energy Policy and Innovation Center\u0027s (\u003Ca href=\u0022https:\/\/epicenter.energy.gatech.edu\/\u0022\u003EEPIcenter\u003C\/a\u003E) Summer Research Program. The competitive program provides a full summer-semester stipend, along with mentorship and professional development opportunities, to support emerging energy scholars.\u003C\/p\u003E\u003Cp\u003E\u0022One of the goals of the program is to give students the time and support needed to make meaningful progress on their dissertation research while helping them understand the broader policy, economic, and societal implications of their work,\u0022 said\u0026nbsp;\u003Ca href=\u0022https:\/\/energy.gatech.edu\/people\/laura-taylor\u0022\u003ELaura Taylor\u003C\/a\u003E, director of EPIcenter.\u003C\/p\u003E\u003Cp\u003EThe stipends enable participants to focus exclusively on clearly defined research goals. The program also supports peer discussions, communication training, and interdisciplinary learning opportunities designed to strengthen both their research and professional development.\u003C\/p\u003E\u003Cp\u003EThis year\u0027s cohort explored topics ranging from electricity markets and air pollution to critical mineral supply chains and grid modernization, highlighting the breadth of energy-related research taking place across Georgia Tech.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EExploring Complex Energy Challenges\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/www.linkedin.com\/in\/anamazmishvili\/\u0022\u003EAna Mazmishvili\u003C\/a\u003E, who studies environmental and energy economics, used the summer to examine how climate policies affect communities across state lines.\u003C\/p\u003E\u003Cp\u003E\u0022My research measures who is actually exposed to pollution from power plants when some states adopt climate regulations to cut emissions while neighboring regions do not,\u0022 Mazmishvili said. \u0022Because air doesn\u0027t stop at state borders, the key question is what happens once the pollution is emitted, and who ends up breathing it.\u0022\u003C\/p\u003E\u003Cp\u003EHer work focuses on the Regional Greenhouse Gas Initiative (RGGI), a cap-and-trade program in the Northeast, and investigates whether the benefits and burdens of emissions reductions are distributed equitably between regulated and neighboring states.\u003C\/p\u003E\u003Cp\u003EMazmishvili said the program provided valuable time to focus on her job-market paper, a central component of her dissertation.\u003C\/p\u003E\u003Cp\u003E\u0022The regular meetings with the program director and other fellows create useful accountability checkpoints and let me hear perspectives from people in very different fields,\u0022 she said. \u0022We\u0027re also learning how to make academic research understandable to a general audience, a skill I expect to use well past this summer.\u0022\u003C\/p\u003E\u003Cp\u003EIndustrial and systems engineering doctoral student\u0026nbsp;\u003Ca href=\u0022https:\/\/www.linkedin.com\/in\/faezeh-fahimy-8ba9a81b9\/\u0022\u003EFaeze Fahimi Aghda\u003C\/a\u003E spent the summer developing an optimization model for the U.S. gallium supply chain, a critical component of many advanced technologies.\u003C\/p\u003E\u003Cp\u003EHer research uses mathematical modeling to examine where and when domestic gallium processing facilities should be established under the threat of supply disruptions.\u003C\/p\u003E\u003Cp\u003E\u0022Working on my research through EPIcenter has taught me to look at my problem from a policy point of view rather than focusing only on the math,\u0022 Fahimi Aghda said. \u0022The feedback within the meetings helped me improve my model.\u0022\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/www.linkedin.com\/in\/ryan-anthony-17239b13b\/\u0022\u003ERyan Anthony\u003C\/a\u003E, in the Jimmy and Rosalynn Carter School of Public Policy, explored how one of the largest oil shocks in U.S. history affected electricity customers and whether utility ownership influenced the impact on consumers.\u003C\/p\u003E\u003Cp\u003E\u0022So far, my research suggests that it mattered a lot,\u201d Anthony said. \u201cMunicipal utilities held rates down and absorbed many of the costs, while private, investor-owned utilities passed more costs through to their customers.\u0022\u003C\/p\u003E\u003Cp\u003EAnthony said the program provided critical support for the archival research required for the project.\u003C\/p\u003E\u003Cp\u003E\u0022My project depends on data that only exists in old government reports, and that kind of archival work is difficult to fund,\u0022 he said. \u0022EPIcenter gave me the time and space to do it properly.\u0022\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EConnecting Research to Real-World Impact\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EFor Samin Alipour, the summer provided an opportunity to explore how electric grids can adapt to growing numbers of distributed energy resources.\u003C\/p\u003E\u003Cp\u003E\u0022Most electric distribution systems were built like one-way roads, carrying power from a substation to homes and businesses,\u0022 Alipour said. \u0022Rooftop solar, batteries, and electric vehicles are turning those roads into two-way systems.\u0022\u003C\/p\u003E\u003Cp\u003EHer research examines how these emerging technologies can be coordinated to increase grid flexibility and clean energy adoption while maintaining safety and reliability and ensuring that costs and benefits are distributed fairly.\u003C\/p\u003E\u003Cp\u003EWith support from EPIcenter, Alipour focused on the economic and policy dimensions of those challenges. \u0022I did not want my research to remain only a technical model,\u0022 she said. \u0022The program has helped me connect the technical results of my dissertation to economic value, reliability, equity and compensation policy.\u0022\u003C\/p\u003E\u003Cp\u003EOne study developed during the summer was accepted for presentation at a specialized power systems conference, an achievement Alipour credits in part to the opportunity to focus on the broader implications of her work.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBuilding the Next Generation of Energy Scholars\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EBeyond advancing individual research projects, the Summer Research Program encourages students to engage with colleagues from different disciplines and develop skills for communicating complex ideas to broader audiences.\u003C\/p\u003E\u003Cp\u003E\u201cThrough regular cohort meetings, participants build a community of accountability, discuss research challenges, explore interdisciplinary energy topics, and develop communication skills,\u201d said\u0026nbsp;\u003Ca href=\u0022https:\/\/energy.gatech.edu\/people\/gilbert-x-gonzalez\u0022\u003EGil Gonzalez\u003C\/a\u003E, program support coordinator for EPIcenter. \u201cStudents also write a research-focused blog post for EPIcenter and present their work at the program\u0027s fall workshop, which allows them to share their research with the broader Georgia Tech energy community.\u201d\u003C\/p\u003E\u003Cp\u003EAs EPIcenter continues to support interdisciplinary energy scholarship at Georgia Tech, the Summer Research Program equips future leaders with the tools to address complex energy challenges through technological innovation, informed policy, and economic analysis.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EFour Georgia Tech doctoral students spent the summer working on their dissertation research through the Energy Policy and Innovation Center\u0027s (\u003Ca href=\u0022https:\/\/epicenter.energy.gatech.edu\/\u0022\u003EEPIcenter\u003C\/a\u003E) Summer Research Program. The competitive program provides a full summer-semester stipend, along with mentorship and professional development opportunities, to support emerging energy scholars.\u003C\/p\u003E\u003Cp\u003E\u0022One of the goals of the program is to give students the time and support needed to make meaningful progress on their dissertation research while helping them understand the broader policy, economic, and societal implications of their work,\u0022 said\u0026nbsp;\u003Ca href=\u0022https:\/\/energy.gatech.edu\/people\/laura-taylor\u0022\u003ELaura Taylor\u003C\/a\u003E, director of EPIcenter.\u003C\/p\u003E\u003Cp\u003EThe stipends enable participants to focus exclusively on clearly defined research goals. The program also supports peer discussions, communication training, and interdisciplinary learning opportunities designed to strengthen both their research and professional development.\u003C\/p\u003E\u003Cp\u003EThis year\u0027s cohort explored topics ranging from electricity markets and air pollution to critical mineral supply chains and grid modernization, highlighting the breadth of energy-related research taking place across Georgia Tech.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Four Georgia Tech doctoral students spent the summer working on their dissertation research through the Energy Policy and Innovation Center\u0027s (EPIcenter) Summer Research Program. "}],"uid":"36413","created_gmt":"2026-08-18 17:15:39","changed_gmt":"2026-08-18 17:21:43","author":"pdevarajan3","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-08-18T00:00:00-04:00","iso_date":"2026-08-18T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"680906":{"id":"680906","type":"image","title":"Students-PhotoCollage.png","body":"\u003Cp\u003E\u003Cem\u003EFrom Top Left (Clockwise): \u003C\/em\u003EAna Mazmishvili, Ryan Anthony, Samin Alipour, Faeze Fahimi Aghda\u003C\/p\u003E","created":"1787073357","gmt_created":"2026-08-18 17:15:57","changed":"1787073357","gmt_changed":"2026-08-18 17:15:57","alt":"From Top Left (clockwise): Ana Mazmishvili, Ryan Anthony, Samin Alipour, Faeze Fahimi Aghda","file":{"fid":"265239","name":"Students-PhotoCollage.png","image_path":"\/sites\/default\/files\/2026\/08\/18\/Students-PhotoCollage.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/08\/18\/Students-PhotoCollage.png","mime":"image\/png","size":1664395,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/08\/18\/Students-PhotoCollage.png?itok=F9-gHuBL"}}},"media_ids":["680906"],"groups":[{"id":"1278","name":"College of Sciences"},{"id":"1188","name":"Research Horizons"},{"id":"367481","name":"SEI Energy"},{"id":"1280","name":"Strategic Energy Institute"}],"categories":[{"id":"131","name":"Economic Development and Policy"},{"id":"144","name":"Energy"},{"id":"135","name":"Research"},{"id":"8862","name":"Student Research"},{"id":"194612","name":"Workforce Development"}],"keywords":[{"id":"186858","name":"go-sei"},{"id":"187915","name":"go-researchnews"},{"id":"188776","name":"go-research"}],"core_research_areas":[{"id":"39531","name":"Energy and Sustainable Infrastructure"},{"id":"39511","name":"Public Service, Leadership, and Policy"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003E\u003Ca href=\u0022mailto:priya.devarajan@research.gatech.edu\u0022\u003EPriya Devarajan\u003C\/a\u003E | SEI Communications Manager\u003C\/p\u003E","format":"limited_html"}],"email":["priya.devarajan@research.gatech.edu"],"slides":[],"orientation":[],"userdata":""}},"691342":{"#nid":"691342","#data":{"type":"news","title":"A New Era of Black Hole Detection","body":[{"value":"\u003Cp dir=\u0022ltr\u0022\u003EThe LIGO\u2013Virgo\u2013KAGRA (LVK) detector network comprises three centers across the globe. The United States hosts twin Laser Interferometer Gravitational-Wave Observatory (LIGO) detectors, one located at Hanford Observatory in Washington State and a second at Livingston Observatory in Louisiana. The Virgo detector is hosted by the European Gravitational Observatory in Italy, and the Kamioka Gravitational Wave (KAGRA) detector is hosted in Japan by the Institute for Cosmic Ray Research (ICRR) of the University of Tokyo.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003EResearchers at Georgia Tech play a key role in the international collaboration. The\u0026nbsp;\u003Ca href=\u0022https:\/\/sites.gatech.edu\/ligo\/people\/\u0022\u003EGeorgia Tech-LIGO research group\u003C\/a\u003E includes\u0026nbsp;\u003Ca href=\u0022https:\/\/physics.gatech.edu\/\u0022\u003ESchool of Physics\u003C\/a\u003E Professor\u0026nbsp;\u003Ca href=\u0022https:\/\/physics.gatech.edu\/user\/laura-cadonati\u0022\u003E\u003Cstrong\u003ELaura Cadonati\u003C\/strong\u003E\u003C\/a\u003E, Assistant Professor\u003Cstrong\u003E\u0026nbsp;\u003C\/strong\u003E\u003Ca href=\u0022https:\/\/physics.gatech.edu\/user\/surabhi-sachdev\u0022\u003E\u003Cstrong\u003ESurabhi Sachdev\u003C\/strong\u003E\u003C\/a\u003E, Research Scientist\u0026nbsp;\u003Ca href=\u0022http:\/\/physics.gatech.edu\/user\/margaret-millhouse\u0022\u003E\u003Cstrong\u003EMargaret Millhouse\u003C\/strong\u003E\u003C\/a\u003E,\u0026nbsp;Postdoctoral Scholar\u0026nbsp;\u003Cstrong\u003EPrathamesh Joshi\u003C\/strong\u003E, eight graduate students, and multiple undergraduates.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003EThe LVK network detects gravitational waves when a massive cosmic event \u2014 like the collision of two black holes \u2014 creates invisible ripples in the fabric of space-time. Waves ripple out at the speed of light, and millions of years after the events that first created them, they reach the LVK detectors.\u0026nbsp;\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003EBut detecting gravitational waves does not simply mean capturing a signal \u2014 clues first need to be untangled from background noise.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003E\u201cIdentifying gravitational-wave signals requires carefully separating real astrophysical events from random fluctuations in the data,\u201d says School of Physics graduate student\u0026nbsp;\u003Ca href=\u0022https:\/\/physics.gatech.edu\/user\/urja-shah\u0022\u003E\u003Cstrong\u003EUrja Shah\u003C\/strong\u003E\u003C\/a\u003E, whose work to quickly identify phenomena supports rapid follow-up by the broader astronomical community.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003ETo support the identification of phenomena, School of Physics graduate student\u0026nbsp;\u003Ca href=\u0022https:\/\/physics.gatech.edu\/user\/megan-arogeti\u0022\u003E\u003Cstrong\u003EMegan Arogeti\u003C\/strong\u003E\u003C\/a\u003E conducts consistency tests between waveforms, checking results to find unexpected or unusual features. \u201cTests like this give us confidence in our models as we continue to observe gravitational waves with increasing sensitivity,\u201d she explains. \u201cThey support new observations and help identify exciting new physics.\u201d\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003E\u201cThese efforts help ensure that gravitational-wave signals are robustly identified and accurately characterized, turning each detection into a precise measurement,\u201d adds Shah. \u201cIn turn, these measurements deepen our understanding of some of the most massive and dense objects in the universe and the fundamental laws governing the cosmos.\u201d\u003C\/p\u003E\u003Ch3 dir=\u0022ltr\u0022\u003EAstrocalibration Autotune\u003C\/h3\u003E\u003Cp dir=\u0022ltr\u0022\u003EWhen a sensor detects a gravitational wave, it produces a distinctive response, says School of Physics graduate student\u0026nbsp;\u003Ca href=\u0022https:\/\/physics.gatech.edu\/user\/shobhit-ranjan\u0022\u003E\u003Cstrong\u003EShobhit Ranjan\u003C\/strong\u003E\u003C\/a\u003E. \u201cThose signals encode a wealth of information we can analyze to learn about their sources \u2014 their masses, spins, distance, and location.\u201d But in order to detect these chirps, the detectors must be carefully calibrated, and if calibration is not optimal, the signals can be compromised.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003ENow,\u0026nbsp;\u003Ca href=\u0022https:\/\/ligo.org\/gravitational-wave-detectors-can-now-autotune-their-signals\/\u0022\u003Ea new tool\u003C\/a\u003E is helping the LVK collaboration recalibrate less optimal signals.\u0026nbsp;The technique is already showing promise: In\u0026nbsp;\u003Ca href=\u0022https:\/\/journals.aps.org\/prl\/accepted\/10.1103\/gzrj-mwv3\u0022\u003Ean article recently accepted in\u0026nbsp;\u003Cem\u003EPhysical Review Letters\u003C\/em\u003E\u003C\/a\u003E, LVK researchers successfully applied it to two interesting signals. The first signal served as a testing opportunity for the method. The team used astrocalibration to recover the data and check it against secondary independent calibration data that was available. They then put the technique to use, recovering information from a second event where no secondary calibration data were available.\u0026nbsp;\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003E\u201cLike autotune in the music industry, the new research shows that theoretical models can be used as guides, similar to how sheet music can help a studio shift off-key music to its correct tone,\u201d Ranjan explains. \u201cThese theoretical models suggest the shape of the signal, and together with data from other detectors, we can adjust the data and read it correctly.\u201d\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003E\u201cThe fact that these detectors can now not only sense cosmic events, but leverage them to improve the data being collected marks a new era in gravitational wave science,\u201d he adds.\u003C\/p\u003E\u003Ch3 dir=\u0022ltr\u0022\u003EA Record-Setting Dataset\u003C\/h3\u003E\u003Cp dir=\u0022ltr\u0022\u003EThe LVK Collaboration also\u0026nbsp;\u003Ca href=\u0022https:\/\/www.ligo.caltech.edu\/news\/ligo20260526\u0022\u003Epublished their fifth catalog of gravitational wave events\u003C\/a\u003E this spring. The findings include an updated estimate of how fast the universe is expanding, evidence for the existence of second-generation black holes, the most precise sky localization ever achieved for a gravitational wave source, and the first measurement of three vibrational modes of a black hole.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003E\u201cOur group helped enable 140 detections out of the 161 reported in this catalog,\u201d says Joshi, who contributed to one of the flagship searches and designed a specialized search focused on detecting especially heavy black hole mergers.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003EJoshi also worked on determining precise locations of where the gravitational waves originated from in the universe \u2014 research that he says will allow astronomers around the world to perform long-term follow-up observations of interesting events.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003EOne record-setting detection showed two black holes that had violently collided more than 3 billion light-years from Earth. Researchers were able to pinpoint its location in the sky more precisely than any other gravitational wave event observed before.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003EImprovements in the LVK network\u2019s ability to localize events along with the large number of detections allowed for a better estimate of the Hubble constant, which measures the rate at which the universe is expanding. The new measurement is over 25% more precise than previous estimates.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003EThe new catalog also includes the \u201cclearest\u201d gravitational wave signal ever detected. The clarity of the signal led to the most accurate test of general relativity ever performed and confirmation of Stephen Hawking\u2019s black hole area theorem.\u003C\/p\u003E\u003Cp dir=\u0022ltr\u0022\u003E\u201cThis catalog provides not just the largest number of black hole detections, it marks a new era of rapid progress,\u201d Sachdev says. \u201cThis is just the beginning of what these observations will allow us to uncover.\u201d\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp dir=\u0022ltr\u0022\u003E\u003Cem\u003EFrom new calibration tools to a record-breaking catalog of detections, the LIGO\u2013Virgo\u2013KAGRA (LVK) detector network is leading the way in gravitational wave science.\u003C\/em\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"From new calibration tools to a record-breaking catalog of detections, the LIGO\u2013Virgo\u2013KAGRA (LVK) detector network is leading the way in gravitational wave science."}],"uid":"35599","created_gmt":"2026-07-29 18:01:53","changed_gmt":"2026-07-31 14:45:16","author":"sperrin6","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-07-29T00:00:00-04:00","iso_date":"2026-07-29T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"680716":{"id":"680716","type":"image","title":"An artist\u0027s concept showing a black hole. (Credit: NASA\/JPL)","body":"\u003Cp\u003EAn artist\u0027s concept showing a black hole. (Credit: NASA\/JPL)\u003C\/p\u003E","created":"1785348119","gmt_created":"2026-07-29 18:01:59","changed":"1785348119","gmt_changed":"2026-07-29 18:01:59","alt":"An artist\u0027s concept showing a black hole. (Credit: NASA\/JPL)","file":{"fid":"265021","name":"black-hole.jpg","image_path":"\/sites\/default\/files\/2026\/07\/29\/black-hole.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/07\/29\/black-hole.jpg","mime":"image\/jpeg","size":222604,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/07\/29\/black-hole.jpg?itok=kXTyscxE"}}},"media_ids":["680716"],"related_links":[{"url":"https:\/\/ligo.org\/science-summaries\/gw240925-gw250207-astro-calibration\/","title":"Tuning our detectors using cosmic collisions"},{"url":"https:\/\/ligo.org\/gwtc-5-0-updated-ligo-virgo-kagra-catalog-sets-new-records-in-precision-gravitational-wave-astronomy\/","title":"GWTC-5.0: Updated LIGO\u2013Virgo\u2013KAGRA Catalog sets new records in precision gravitational wave astronomy"},{"url":"https:\/\/ligo.org\/gravitational-wave-detectors-can-now-autotune-their-signals\/","title":"Gravitational wave detectors can now \u2018autotune\u2019 their signals"}],"groups":[{"id":"1278","name":"College of Sciences"},{"id":"1188","name":"Research Horizons"},{"id":"126011","name":"School of Physics"}],"categories":[{"id":"150","name":"Physics and Physical Sciences"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[{"id":"192252","name":"cos-planetary"},{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"193657","name":"Space Research Initiative"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003E\u003Ca href=\u0022mailto:sperrin6@gatech.edu\u0022\u003ESelena Langner\u0026nbsp;\u003C\/a\u003E\u003Cbr\u003ETechnical Research Writer \/ Editor\u0026nbsp;\u003Cbr\u003EGeorgia Tech College of Sciences\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}},"690884":{"#nid":"690884","#data":{"type":"news","title":"ICSFlux: Using Physics to Uncover Cyberthreats ","body":[{"value":"\u003Cp\u003EThe factories, water utilities, and power systems that keep daily life running rest on the assumption that as long as no one breaks into the computers that run the equipment, the equipment stays safe.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ELogically this makes sense and has been backed up by past security research. However, researchers at Georgia Tech have found hidden paths in cyber-physical systems that attackers can use to disrupt or even destroy them.\u003C\/p\u003E\u003Cp\u003ETo find these hidden paths before an attacker does, the researchers built a testing tool called ICSFlux. This new tool leans on the physics used by the industrial process and maps out the system to find new threats that were once thought impossible.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EICSFlux was deployed across 11 different programmable logic controllers in six industrial sectors, including chemical manufacturing, water treatment, power grids, aircraft, desalination, and waste processing. The process uncovered twenty genuine safety violations.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EIn one case drawn from a chemical-plant simulation, an attack path uncovered by the tool drove a reactor past its safe pressure limit and into a simulated explosion. By using nothing but valid operator commands, the team took the reactor from a completely normal and stable state to critical territory.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EBecause the method relies only on the physics of a process and not on the details of any one controller, the same tool worked across all six sectors without being rebuilt, and it reduced the search space by roughly 50%.\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/sahinburak.github.io\/\u0022\u003E\u003Cstrong\u003EBurak Sahin\u003C\/strong\u003E\u003C\/a\u003E, a Ph.D. student at Georgia Tech and the study\u0027s lead author, found that by sending a series of perfectly normal, fully authorized commands, intruders can slowly nudge a physical process toward a dangerous state.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cThese systems are usually judged safe as long as nobody hacks into them,\u0027\u0027 Sahin said. \u201cWhat we found is that an attacker who can send everyday commands, the same ones a normal operator sends, can patiently steer the process toward a failure. No single command looks wrong, which is exactly why the usual defenses miss it.\u0027\u0027\u003C\/p\u003E\u003Cp\u003EMost existing tools assume an attacker can rewire the controller or change the software inside it. In the real world, those controllers are locked down and cannot be touched. ICSFlux takes the opposite and more realistic view. It treats the controller as a sealed box that cannot be opened and works only with the commands an operator is normally allowed to send.\u003C\/p\u003E\u003Cp\u003ERather than measuring how much of a controller\u0027s software it has exercised, the usual yardstick for this kind of testing, ICSFlux measures how close the physical system is getting to an unsafe limit and steers its testing in that direction.\u003C\/p\u003E\u003Cp\u003E\u201cTwo different sensor readings can run through the exact same code and still send a reactor in completely different directions,\u0027\u0027 Sahin said. \u201cLooking only at the software tells you nothing about whether the physical system is safe. We had to follow the physics, not the code.\u0027\u0027\u003C\/p\u003E\u003Cp\u003EOne of the study\u0027s most important takeaways emerged when the researchers tightened the safety margins to see whether caution alone would help. Even when every command stayed within approved limits, the way the controller reacted to a steady stream of small adjustments could still cause pressure to overshoot and the reactor to fail. In other words, staying inside the rules was not always enough.\u003C\/p\u003E\u003Cp\u003EAll of the team\u0027s experiments were carried out on secured, controlled test beds. The work was conducted with Georgia Tech\u0027s \u003Ca href=\u0022https:\/\/sites.gatech.edu\/capcpsec\/\u0022\u003ECyber-Physical Systems Security Lab\u003C\/a\u003E, whose research spans the security of cyber-physical systems from industrial programmable logic controllers to marine, automotive, and drone platforms. Georgia Tech\u0027s \u003Ca href=\u0022https:\/\/cyfi.ece.gatech.edu\/\u0022\u003ECyber Forensics Innovation Laboratory\u003C\/a\u003E, a team of researchers who work together to further the investigation of advanced cyber crimes and the analysis and prevention of next-generation malware attacks, also contributed to the paper.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe labs are a collaboration between the \u003Ca href=\u0022https:\/\/scp.cc.gatech.edu\/\u0022\u003ESchool of Cybersecurity and Privacy\u003C\/a\u003E and the \u003Ca href=\u0022https:\/\/ece.gatech.edu\/\u0022\u003ESchool of Electrical and Computer Engineering\u003C\/a\u003E.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EFuzzing the Physical Space: Physics-Aware Testing of Black-Box Industrial Control Systems\u003C\/em\u003E\u0027 was accepted to the \u003Ca href=\u0022https:\/\/sp2026.ieee-security.org\/\u0022\u003E2026 IEEE Symposium on Security and Privacy\u003C\/a\u003E. In addition to Sahin, the team includes Ph.D. students \u003Cstrong\u003EDavid Oygenblik\u003C\/strong\u003E, \u003Cstrong\u003EMingxuan Yao\u003C\/strong\u003E, and \u003Cstrong\u003EYizhi Huang \u003C\/strong\u003Eas well as Associate Professors \u003Cstrong\u003EBrendan Saltaformaggio\u003C\/strong\u003E, and \u003Cstrong\u003ESaman Zonouz\u003C\/strong\u003E.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EThe factories, water utilities, and power systems that keep daily life running rest on the assumption that as long as no one breaks into the computers that run the equipment, the equipment stays safe.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ELogically this makes sense and has been backed up by past security research. However, researchers at Georgia Tech have found hidden paths in cyber-physical systems that attackers can use to disrupt or even destroy them.\u003C\/p\u003E\u003Cp\u003ETo find these hidden paths before an attacker does, the researchers built a testing tool called ICSFlux. This new tool leans on the physics used by the industrial process and maps out the system to find new threats that were once thought impossible.\u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"To find hidden vulnerabilites before an attacker does, researchers built a testing tool called ICSFlux that leans on the physics used by the industrial process and maps out the system to find new threats once thought impossible. "}],"uid":"36253","created_gmt":"2026-06-24 14:57:00","changed_gmt":"2026-06-24 15:10:58","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-06-24T00:00:00-04:00","iso_date":"2026-06-24T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"680500":{"id":"680500","type":"image","title":"utilities.jpg","body":null,"created":"1782313123","gmt_created":"2026-06-24 14:58:43","changed":"1782313123","gmt_changed":"2026-06-24 14:58:43","alt":"A collection of utilities like power plants, geothermal stations, solar farms, etc.","file":{"fid":"264773","name":"utilities.jpg","image_path":"\/sites\/default\/files\/2026\/06\/24\/utilities.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/06\/24\/utilities.jpg","mime":"image\/jpeg","size":3540206,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/06\/24\/utilities.jpg?itok=RC1Hy0vy"}},"680501":{"id":"680501","type":"image","title":"Burak-Sahin.jpg","body":"\u003Cp\u003E\u003Cstrong\u003EBurak Sahin\u003C\/strong\u003E, a Ph.D. Candidate in Computer Science at the \u003Ca href=\u0022https:\/\/www.gatech.edu\/\u0022\u003EGeorgia Institute of Technology\u003C\/a\u003E, advised by \u003Ca href=\u0022https:\/\/sites.google.com\/site\/samanzonouz4n6\/saman-zonouz\u0022\u003ESaman Zonouz\u003C\/a\u003E (\u003Ca href=\u0022https:\/\/sites.gatech.edu\/capcpsec\/\u0022\u003ECPSec Lab\u003C\/a\u003E) and co-advised by \u003Ca href=\u0022https:\/\/saltaformaggio.ece.gatech.edu\/\u0022\u003EBrendan Saltaformaggio\u003C\/a\u003E (\u003Ca href=\u0022https:\/\/cyfi.ece.gatech.edu\/\u0022\u003ECyFI Lab\u003C\/a\u003E)\u003C\/p\u003E","created":"1782313398","gmt_created":"2026-06-24 15:03:18","changed":"1782313398","gmt_changed":"2026-06-24 15:03:18","alt":"A side profile of a man\u0027s face. He has long hair and a beard","file":{"fid":"264774","name":"Burak-Sahin.jpg","image_path":"\/sites\/default\/files\/2026\/06\/24\/Burak-Sahin.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/06\/24\/Burak-Sahin.jpg","mime":"image\/jpeg","size":75559,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/06\/24\/Burak-Sahin.jpg?itok=3mVGJ9eI"}}},"media_ids":["680500","680501"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"660406","name":"School of Cybersecurity \u0026 Privacy"},{"id":"660367","name":"School of Cybersecurity and Privacy"}],"categories":[{"id":"42901","name":"Community"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"150","name":"Physics and Physical Sciences"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[],"core_research_areas":[{"id":"145171","name":"Cybersecurity"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJohn Popham\u003C\/p\u003E\u003Cp\u003ECommunications Officer II at the School of Cybersecurity and Privacy\u003C\/p\u003E","format":"limited_html"}],"email":["jpopham3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}