{"678269":{"#nid":"678269","#data":{"type":"news","title":"AI Model Creates Invisible Digital Masks to Defend Against Unwanted Facial Recognition","body":[{"value":"\u003Cp\u003EJust as a chameleon changes colors to mask itself from predators, new AI-powered technology is protecting people\u2019s photos from online privacy threats.\u003C\/p\u003E\u003Cp\u003EThe innovative model, developed at Georgia Tech, creates invisible digital masks for personal photos to thwart unwanted online facial recognition while preserving the image quality.\u003C\/p\u003E\u003Cp\u003EAnyone who posts photos of themselves risks having their privacy violated by unauthorized facial image collection. Online criminals and other bad actors collect facial images by web scraping to create databases.\u003C\/p\u003E\u003Cp\u003EThese illicit databases enable criminals to commit identity fraud, stalking, and other crimes. The practice also opens victims to unwanted targeted ads and attacks.\u003C\/p\u003E\u003Cp\u003EThe new model is called Chameleon. Unlike current models, which produce different masks for each user\u2019s photos, Chameleon creates a single, personalized privacy protection (P-3) mask for all of a user\u2019s facial photos.\u003C\/p\u003E\u003Cp\u003EA bespoke P-3 mask is created based on a few user-submitted facial photos. After applying the mask, protected photos won\u2019t be detectable by someone scanning for the user\u2019s face. Instead, the unwanted scan will identify the protected photos as being someone else.\u003C\/p\u003E\u003Cp\u003EThe Chameleon model was developed by Professor \u003Ca href=\u0022https:\/\/faculty.cc.gatech.edu\/~lingliu\/\u0022\u003E\u003Cstrong\u003ELing Liu\u003C\/strong\u003E\u003C\/a\u003E of the School of Computer Science (SCS), Ph.D. students \u003Ca href=\u0022https:\/\/bayi-hu.github.io\/\u0022\u003E\u003Cstrong\u003ESihao Hu\u003C\/strong\u003E\u003C\/a\u003E and \u003Ca href=\u0022https:\/\/huangtiansheng.github.io\/\u0022\u003E\u003Cstrong\u003ETiansheng Huang\u003C\/strong\u003E\u003C\/a\u003E, and \u003Ca href=\u0022https:\/\/khchow.com\/\u0022\u003E\u003Cstrong\u003EKa-Ho Chow\u003C\/strong\u003E\u003C\/a\u003E, an assistant professor at the University of Hong Kong and Liu\u2019s former Ph.D. student.\u003C\/p\u003E\u003Cp\u003EDuring development, the team accomplished its two main goals: protecting the person\u0027s identity in the photo and ensuring a minimal visual difference between the original and masked photos.\u003C\/p\u003E\u003Cp\u003EThe researchers said a notable visual difference often exists between the original and photos using current masking models. However, Chameleon preserves much of the original photo\u2019s quality among various facial images.\u003C\/p\u003E\u003Cp\u003EIn several research tests, Chameleon outperformed three top facial recognition protection models in visual and protective metrics. The tests also showed that Chameleon offers more substantial privacy protection while being faster and more resource-efficient.\u003C\/p\u003E\u003Cp\u003EIn the future, Huang said they would like to apply Chameleon\u2019s methods to other uses.\u003C\/p\u003E\u003Cp\u003E\u201cWe would like to use these techniques to protect images from being used to train artificial intelligence generative models. We could protect the image information from being used without consent,\u201d he said.\u003C\/p\u003E\u003Cp\u003EThe research team aims to release Chameleon code publicly on GitHub to allow others to improve their work.\u003C\/p\u003E\u003Cp\u003E\u201cPrivacy-preserving data sharing and analytics like Chameleon will help to advance governance and responsible adoption of AI technology and stimulate responsible science and innovation,\u201d said Liu.\u003C\/p\u003E\u003Cp\u003EThe paper on Chameleon, \u003Cem\u003EPersonalized Privacy Protection Mask Against Unauthorized Facial Recognition\u003C\/em\u003E, was presented earlier this month at ECCV 2024.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EA new new AI-powered technology is protecting people\u2019s photos from online privacy threats. The technology, Chameleon, creates invisible digital masks for personal photos to thwart unwanted online facial recognition while preserving the image quality.\u003C\/p\u003E\u003Cp\u003E\u003Cbr\u003E\u003Cbr\u003E\u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"A new new AI-powered technology is protecting people\u2019s photos from online privacy threats."}],"uid":"36532","created_gmt":"2024-11-07 20:24:54","changed_gmt":"2024-11-08 15:19:42","author":"Morgan Usry","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2024-11-07T00:00:00-05:00","iso_date":"2024-11-07T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"675550":{"id":"675550","type":"image","title":"Chameleonstory.jpg","body":null,"created":"1731011119","gmt_created":"2024-11-07 20:25:19","changed":"1731011119","gmt_changed":"2024-11-07 20:25:19","alt":"A digital face","file":{"fid":"259187","name":"Chameleonstory.jpg","image_path":"\/sites\/default\/files\/2024\/11\/07\/Chameleonstory.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/11\/07\/Chameleonstory.jpg","mime":"image\/jpeg","size":329962,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/11\/07\/Chameleonstory.jpg?itok=cZWadnnM"}}},"media_ids":["675550"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"50875","name":"School of Computer Science"}],"categories":[{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"135","name":"Research"}],"keywords":[{"id":"10199","name":"Daily Digest"},{"id":"187915","name":"go-researchnews"},{"id":"1404","name":"Cybersecurity"},{"id":"174713","name":"facial recognition"},{"id":"187812","name":"artificial intelligence (AI)"}],"core_research_areas":[{"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\u003EMorgan Usry, Communications Officer, School of Computer Science\u003C\/p\u003E","format":"limited_html"}],"email":["morgan.usry@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}