{"id":49644,"date":"2021-09-17T12:28:09","date_gmt":"2021-09-17T09:28:09","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=49644"},"modified":"2025-09-02T13:42:08","modified_gmt":"2025-09-02T10:42:08","slug":"scientists-fool-a-facial-recognition-system-with-natural-makeup","status":"publish","type":"post","link":"https:\/\/u1f987.com\/en\/scientists-fool-a-facial-recognition-system-with-natural-makeup\/","title":{"rendered":"Scientists fool a facial-recognition system with natural makeup"},"content":{"rendered":"

A group of scientists in collaboration with the Japanese NEC conducted<\/a> a laboratory experiment, during which they attempted to fool the facial-recognition system by applying natural makeup to the subjects.<\/p>\n

According to the researchers, natural makeup is hard to spot with the naked eye and its use would not raise suspicions.<\/p>\n

\n

“Our method detects natural makeup that, when applied to the attacker\\’s face, hides his or her identity from the facial-recognition system,” they say.<\/p>\n<\/blockquote>\n

The scientists loaded into the surrogate model photographs of \u00abblacklisted\u00bb<\/span> individuals to create a heat map showing the most important regions for identifying a given person.<\/p>\n

Then, on these areas they applied makeup to alter the appearance of the participants.<\/p>\n

For example, powder narrowed the nose, and contouring made the cheekbones more pronounced.<\/p>\n

The researchers repeated this process until they managed to fool the model.<\/p>\n

\\\"The
The surrogate model labeled a well-known participant as unknown after makeup. Data: study.<\/figcaption><\/figure>\n

\\n<\/p>\n

In a small experiment conducted on ten men and ten women aged 20 to 28, facial-recognition cameras correctly identified the “blacklisted” people with makeup in 1.22% of cases.<\/p>\n

The baseline model itself was not highly accurate. According to the study, it correctly identified participants without makeup in only 47.57% of cases, while with makeup applied, the rate dropped to 33.73%.<\/p>\n

The researchers say that the drop in facial-recognition performance with makeup is below the realistic threshold for a real-world operating environment.<\/p>\n

Earlier this year, scientists generated an image of a “universal face”, capable of deceiving most biometric identification systems<\/a>.<\/p>\n

In July, researchers reported the discovery of a method for unobtrusive insertion of malware<\/a> into neural networks.<\/p>\n

In May, researchers from the Maryland Center for Cybersecurity identified a vulnerability in neural networks<\/a> that increases their energy consumption.<\/p>\n

Subscribe to ForkLog’s AI news on Telegram: ForkLog AI<\/a> \u2014 all the news from the world of AI!<\/p>\n","protected":false},"excerpt":{"rendered":"

A group of scientists in collaboration with the Japanese NEC conducted a laboratory experiment in which they attempted to fool a facial-recognition system by applying natural makeup to the subjects.<\/p>\n","protected":false},"author":1,"featured_media":49645,"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":[438,167,1515],"class_list":["post-49644","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-research","tag-tracking"],"aioseo_notices":[],"amp_enabled":true,"views":"25","promo_type":"1","layout_type":"1","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/49644","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=49644"}],"version-history":[{"count":1,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/49644\/revisions"}],"predecessor-version":[{"id":49646,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/posts\/49644\/revisions\/49646"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media\/49645"}],"wp:attachment":[{"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/media?parent=49644"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/categories?post=49644"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/u1f987.com\/en\/wp-json\/wp\/v2\/tags?post=49644"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}