{"id":97403,"date":"2019-10-14T01:22:34","date_gmt":"2019-10-14T08:22:34","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2019\/10\/why-deep-learning-ais-are-so-easy-to-fool"},"modified":"2019-10-14T01:22:34","modified_gmt":"2019-10-14T08:22:34","slug":"why-deep-learning-ais-are-so-easy-to-fool","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2019\/10\/why-deep-learning-ais-are-so-easy-to-fool","title":{"rendered":"Why deep-learning AIs are so easy to fool"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/why-deep-learning-ais-are-so-easy-to-fool3.jpg\"><\/a><\/p>\n<p>These are just some examples of how easy it is to break the leading pattern-recognition technology in AI, known as deep neural networks (DNNs). These have proved incredibly successful at correctly classifying all kinds of input, including images, speech and data on consumer preferences. They are part of daily life, running everything from automated telephone systems to user recommendations on the streaming service Netflix. Yet making alterations to inputs \u2014 in the form of tiny changes that are typically imperceptible to humans \u2014 can flummox the best neural networks around.<\/p>\n<hr>\n<p>Artificial-intelligence researchers are trying to fix the flaws of neural networks.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>These are just some examples of how easy it is to break the leading pattern-recognition technology in AI, known as deep neural networks (DNNs). These have proved incredibly successful at correctly classifying all kinds of input, including images, speech and data on consumer preferences. They are part of daily life, running everything from automated telephone [\u2026]<\/p>\n","protected":false},"author":417,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-97403","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/97403","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/417"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=97403"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/97403\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=97403"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=97403"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=97403"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}