{"id":1101,"date":"2015-04-08T11:30:06","date_gmt":"2015-04-08T11:30:06","guid":{"rendered":"http:\/\/paslongtemps.net\/blog\/2015\/04\/08\/using-artificial-evolution-to-fool-neural-networks\/"},"modified":"2020-04-05T17:14:30","modified_gmt":"2020-04-05T15:14:30","slug":"using-artificial-evolution-to-fool-neural-networks","status":"publish","type":"post","link":"https:\/\/paslongtemps.net\/blog\/2015\/04\/08\/using-artificial-evolution-to-fool-neural-networks\/","title":{"rendered":""},"content":{"rendered":"\n\t\t<style type=\"text\/css\">\n\t\t\t#gallery-1 {\n\t\t\t\tmargin: auto;\n\t\t\t}\n\t\t\t#gallery-1 .gallery-item {\n\t\t\t\tfloat: left;\n\t\t\t\tmargin-top: 10px;\n\t\t\t\ttext-align: center;\n\t\t\t\twidth: 33%;\n\t\t\t}\n\t\t\t#gallery-1 img {\n\t\t\t\tborder: 2px solid #cfcfcf;\n\t\t\t}\n\t\t\t#gallery-1 .gallery-caption {\n\t\t\t\tmargin-left: 0;\n\t\t\t}\n\t\t\t\/* see gallery_shortcode() in wp-includes\/media.php *\/\n\t\t<\/style>\n\t\t<div id='gallery-1' class='gallery galleryid-1101 gallery-columns-3 gallery-size-thumbnail'><dl class='gallery-item'>\n\t\t\t<dt class='gallery-icon landscape'>\n\t\t\t\t<a href='https:\/\/paslongtemps.net\/blog\/2015\/04\/08\/using-artificial-evolution-to-fool-neural-networks\/attachment\/1102\/'><img loading=\"lazy\" decoding=\"async\" width=\"150\" height=\"150\" src=\"https:\/\/paslongtemps.net\/blog\/wp-content\/uploads\/sites\/3\/2015\/04\/tumblr_nmhjy6eYiW1qz9b1ho1_1280-150x150.png\" class=\"attachment-thumbnail size-thumbnail\" alt=\"\" \/><\/a>\n\t\t\t<\/dt><\/dl>\n\t\t\t<br style='clear: both' \/>\n\t\t<\/div>\n\n<p><b>Using artificial evolution to fool neural networks<\/b><\/p>\n<p><a href=\"http:\/\/www.evolvingai.org\/fooling\">http:\/\/www.evolvingai.org\/fooling<\/a><\/p>\n<p>Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images<\/p>\n<blockquote><p>[&hellip;]it is easy to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99.99% confidence (e.g. labeling with certainty that white noise static is a lion)<\/p><\/blockquote>\n<p>This paper from late 2014 got a lot of almost-mainstream press (<a href=\"http:\/\/www.wired.com\/2015\/01\/simple-pictures-state-art-ai-still-cant-recognize\/\">Wired<\/a>, <a href=\"http:\/\/www.theatlantic.com\/technology\/archive\/2014\/12\/how-to-fool-a-computer-with-optical-illusions\/383779\/\">the Atlantic<\/a>, etc), I found it very interesting, not only for the stress they put Deep Neural Networks under (after all I guess it\u2019s always possible to fool a computer), but also for the not mentioned enough use of evolutionary algorithms for generating the trick images. And, it was not a good old genetic algorithm that was used, but rather some interactive evolution, where a human plays the role of the fitness function (see\u00a0<a href=\"http:\/\/picbreeder.org\/\">http:\/\/picbreeder.org\/<\/a>), thereby turning evolution into breeding, much like wheat, or dogs, were bred by men and not a direct product of evolution.<\/p>\n<p>I suspect the paper would not have had the same impact if it had only presented examples with\u00a0\u201cwhite noise-y\u201d pictures.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Using artificial evolution to fool neural networks http:\/\/www.evolvingai.org\/fooling Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images [&hellip;]it is easy to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99.99% confidence (e.g. labeling with certainty that white noise static is a lion) [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"gallery","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-1101","post","type-post","status-publish","format-gallery","hentry","category-uncategorized","post_format-post-format-gallery"],"_links":{"self":[{"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/posts\/1101","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/comments?post=1101"}],"version-history":[{"count":1,"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/posts\/1101\/revisions"}],"predecessor-version":[{"id":1103,"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/posts\/1101\/revisions\/1103"}],"wp:attachment":[{"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/media?parent=1101"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/categories?post=1101"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/paslongtemps.net\/blog\/wp-json\/wp\/v2\/tags?post=1101"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}