{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/face-flashing-a-secure-liveness-detection","title":"Face Flashing: a Secure Liveness Detection Protocol based on Light Reflections","arxiv_id":"1801.01949","date":"2018-01-06","proceeding":null,"authors":["Di Tang","Zhe Zhou","Yinqian Zhang","Kehuan Zhang"],"abstract":"Face authentication systems are becoming increasingly prevalent, especially\nwith the rapid development of Deep Learning technologies. However, human facial\ninformation is easy to be captured and reproduced, which makes face\nauthentication systems vulnerable to various attacks. Liveness detection is an\nimportant defense technique to prevent such attacks, but existing solutions did\nnot provide clear and strong security guarantees, especially in terms of time.\n  To overcome these limitations, we propose a new liveness detection protocol\ncalled Face Flashing that significantly increases the bar for launching\nsuccessful attacks on face authentication systems. By randomly flashing\nwell-designed pictures on a screen and analyzing the reflected light, our\nprotocol has leveraged physical characteristics of human faces: reflection\nprocessing at the speed of light, unique textual features, and uneven 3D\nshapes. Cooperating with working mechanism of the screen and digital cameras,\nour protocol is able to detect subtle traces left by an attacking process.\n  To demonstrate the effectiveness of Face Flashing, we implemented a prototype\nand performed thorough evaluations with large data set collected from\nreal-world scenarios. The results show that our Timing Verification can\neffectively detect the time gap between legitimate authentications and\nmalicious cases. Our Face Verification can also differentiate 2D plane from 3D\nobjects accurately. The overall accuracy of our liveness detection system is\n98.8\\%, and its robustness was evaluated in different scenarios. In the worst\ncase, our system's accuracy decreased to a still-high 97.3\\%.","url_abs":"http://arxiv.org/abs/1801.01949v2","url_pdf":"http://arxiv.org/pdf/1801.01949v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"face-flashing-a-secure-liveness-detection","repo_url":"https://github.com/Faceplugin-ltd/FaceLivenessDetection-Android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"face-verification","task_name":"Face Verification"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}