{"690808":{"#nid":"690808","#data":{"type":"news","title":"Research Gets to the Core of AI Drone Crashes","body":[{"value":"\u003Cp\u003EA drone powered by artificial intelligence crashes in a remote field, destroying its onboard computer and leaving investigators without the data needed to determine whether a cyberattack caused the failure.\u003C\/p\u003E\u003Cp\u003EResearchers at Georgia Tech say they have developed a system to help answer that question.\u003C\/p\u003E\u003Cp\u003EKnown as FIRA, the tool analyzes drone crashes to determine whether they were caused by poisoned machine-learning (ML) models. The team will present its findings at the \u003Ca href=\u0022https:\/\/www.usenix.org\/conference\/usenixsecurity26\u0022\u003E35th USENIX Security Symposium\u003C\/a\u003E in August.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe research addresses a growing safety challenge as drones are increasingly used for deliveries, infrastructure inspections, and agriculture.\u003C\/p\u003E\u003Cp\u003EAs drones rely more on machine learning to navigate and make decisions, they also become vulnerable to model poisoning attacks. In these attacks, adversaries manipulate an AI system during its learning phase, embedding hidden triggers that can cause failures under specific conditions.\u003C\/p\u003E\u003Cp\u003E\u201cMachine learning drones are making more decisions in flight, which makes ML a safety-critical component of these systems,\u201d said\u0026nbsp;\u003Cstrong\u003EYizhi Huang\u003C\/strong\u003E, Ph.D. student and lead researcher on the project.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cWhen something goes wrong, investigators need a way to ask whether the model was responsible, but the model is the part of the system that no one can examine after a crash.\u0026nbsp;FIRA\u0026nbsp;gives investigators a way to investigate these cases by reconstructing what the model was doing during the crash. As more drones run with ML, this kind of forensic capability can help drones be used more effectively and safely.\u201d\u003C\/p\u003E\u003Cp\u003EWhen a drone crashes, investigators must determine whether the cause was malicious interference, weather, or mechanical failure. Without reliable forensic tools, accountability is difficult to establish, and safety standards are harder to enforce.\u003C\/p\u003E\u003Cp\u003EFIRA identifies how drone components interact with machine learning models and monitors those interactions in real time, even with limited bandwidth.\u003C\/p\u003E\u003Cp\u003EThe system functions like a flight recorder, capturing key system activity and reconstructing a timeline after a crash. It then analyzes the model\u2019s behavior to determine whether a malicious trigger was introduced via poisoned ML training data.\u003C\/p\u003E\u003Cp\u003EIn tests across multiple drone platforms and crash scenarios, FIRA identified failure causes and distinguished cyberattacks from environmental or mechanical issues.\u003C\/p\u003E\u003Cp\u003EThe system does not require access to a drone\u2019s source code, making it practical for real-world investigations.\u003C\/p\u003E\u003Cp\u003E\u201cAs commercial drone use expands, tools like FIRA could help improve accountability and trust in AI-powered systems operating in public airspace,\u201d said\u0026nbsp;Huang.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/www.usenix.org\/system\/files\/conference\/usenixsecurity26\/sec26_prepub_huang-yizhi.pdf\u0022\u003E\u003Cem\u003EFIRA: Enabling Automatic Forensic Investigation of Unmanned Aerial Vehicles\u003C\/em\u003E\u003C\/a\u003E was led by Georgia Tech\u2019s \u003Ca href=\u0022https:\/\/cyfi.ece.gatech.edu\/\u0022\u003ECyber Forensics Innovation Lab\u003C\/a\u003E in cooperation with the \u003Ca href=\u0022https:\/\/sites.gatech.edu\/capcpsec\/\u0022\u003ECyber-Physical Security Lab\u003C\/a\u003E. These labs reside in 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 Computing Engineering\u003C\/a\u003E.\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EA drone powered by artificial intelligence crashes in a remote field, destroying its onboard computer and leaving investigators without the data needed to determine whether a cyberattack caused the failure.\u003C\/p\u003E\u003Cp\u003EResearchers at Georgia Tech say they have developed a system to help answer that question.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Researchers at Georgia Tech say they have developed a system to determine whether a cyberattack caused drone crashes."}],"uid":"36253","created_gmt":"2026-06-18 17:32:32","changed_gmt":"2026-06-18 17:54:50","author":"John Popham","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-06-18T00:00:00-04:00","iso_date":"2026-06-18T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"660599":{"id":"660599","type":"image","title":"CyFI Lab Sign","body":null,"created":"1661532564","gmt_created":"2022-08-26 16:49:24","changed":"1661532564","gmt_changed":"2022-08-26 16:49:24","alt":"Sign reading Cyber Forensics Innovation Laboratory The CyFI Lab","file":{"fid":"250302","name":"SCP August 2022-66.png","image_path":"\/sites\/default\/files\/images\/SCP%20August%202022-66.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/SCP%20August%202022-66.png","mime":"image\/png","size":9087261,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/SCP%20August%202022-66.png?itok=7KS9Gbz_"}}},"media_ids":["660599"],"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"}],"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 II at the School of Cybersecurity and Privacy\u003C\/p\u003E","format":"limited_html"}],"email":["jpopham3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}