{"id":47251,"date":"2021-08-05T12:10:23","date_gmt":"2021-08-05T09:10:23","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=47251"},"modified":"2025-09-01T20:21:20","modified_gmt":"2025-09-01T17:21:20","slug":"neural-network-learns-to-fool-identification-systems-with-a-universal-face","status":"publish","type":"post","link":"https:\/\/u1f987.com\/en\/neural-network-learns-to-fool-identification-systems-with-a-universal-face\/","title":{"rendered":"Neural network learns to fool identification systems with a &#8216;universal&#8217; face"},"content":{"rendered":"<p>Researchers at Tel Aviv University in Israel <a href=\\\"https:\/\/arxiv.org\/pdf\/2108.01077.pdf\\\" target=\\\"_blank\\\" rel=\\\"noreferrer noopener nofollow\\\">developed<\/a> a method to bypass biometric identification systems using a forged facial image.<\/p>\n<p><!--more--><\/p>\n<p>The disclosed method uses artificial intelligence technologies to create a universal facial template that can sequentially merge with and unlock identity verification systems.<\/p>\n<p>According to the researchers, the vulnerability lies in the fact that facial recognition uses a wide set of markers to identify specific individuals. With these, a universal template can be created that can fool a large percentage of security systems.<\/p>\n<p>Researchers suggested that as few as nine faces generated by the algorithm <span data-descr=\\\"neural network used to create fake images of human faces\\\" class=\\\"old_tooltip\\\">StyleGAN<\/span> could correspond to 40% of the Earth&#8217;s population. They tested the neural-network-synthesized image on a dataset of 13,000 images and found that the fake face could imitate 20% of the identities in the dataset. Other tests showed higher results.<\/p>\n<blockquote class=\\\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\\\">\n<p>&#8220;Face authentication is extremely vulnerable, even if attackers have no information about the target identity,&#8221; the researchers said.<\/p>\n<\/blockquote>\n<p>The researchers also believe that the vulnerability could be combined with deepfakes to mimic a &#8220;liveness&#8221; check, which is often used for remote identity verification by performing a series of gestures.<\/p>\n<p>Earlier in July, researchers reported the discovery of a method<a href=\"https:\/\/u1f987.com\/en\/news\/researchers-have-learned-to-covertly-embed-malware-in-neural-networks\"> for covertly inserting malicious code into a neural network<\/a>.<\/p>\n<p>In May, researchers from the Maryland Center for Cybersecurity<a href=\"https:\/\/u1f987.com\/en\/news\/researchers-identify-vulnerability-in-neural-networks-that-increases-their-energy-consumption\"> identified a vulnerability in neural networks<\/a> that increases their energy consumption.<\/p>\n<p>Subscribe to ForkLog&#8217;s news on Telegram: <a href=\\\"https:\/\/t.me\/forklogAI\\\" target=\\\"_blank\\\" rel=\\\"noreferrer noopener nofollow\\\"> ForkLog AI<\/a> \u2014 all the news from the world of AI!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Researchers at Tel Aviv University in Israel developed a method to bypass biometric identification systems using a forged facial image.<\/p>\n","protected":false},"author":1,"featured_media":47252,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1111,1515],"class_list":["post-47251","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-cybersecurity","tag-tracking"],"aioseo_notices":[],"amp_enabled":true,"views":"16","promo_type":"1","layout_type":"1","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/47251","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/comments?post=47251"}],"version-history":[{"count":1,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/47251\/revisions"}],"predecessor-version":[{"id":47253,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/47251\/revisions\/47253"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media\/47252"}],"wp:attachment":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media?parent=47251"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/categories?post=47251"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/tags?post=47251"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}