{"id":13571,"date":"2024-08-07T03:25:16","date_gmt":"2024-08-07T07:25:16","guid":{"rendered":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=13571"},"modified":"2024-08-07T03:25:16","modified_gmt":"2024-08-07T07:25:16","slug":"ai-is-vulnerable-to-attack-can-it-ever-be-used-safely","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/ai-is-vulnerable-to-attack-can-it-ever-be-used-safely\/13571\/","title":{"rendered":"AI is vulnerable to attack. Can it ever be used safely?"},"content":{"rendered":"Originally published in nature, July 25, 2024. The models that underpin artificial-intelligence systems such as ChatGPT can be subject to attacks that elicit harmful behaviour. Making them safe will not be easy. In 2015, computer scientist Ian Goodfellow and his colleagues at Google described what could be artificial intelligence\u2019s most famous failure. First, a neural network trained to classify images correctly identified a photograph of a panda. Then Goodfellow\u2019s team added a small amount of carefully calculated noise to the image. The result was indistinguishable to the human eye, but the network now confidently asserted that the image <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/ai-is-vulnerable-to-attack-can-it-ever-be-used-safely\/13571\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Originally published in nature, July 25, 2024. The models that underpin artificial-intelligence systems such as ChatGPT can be subject to attacks that elicit harmful behaviour. Making them safe will not be easy. In 2015, computer scientist Ian Goodfellow and his colleagues at Google described what could be artificial intelligence\u2019s most famous failure. First, a neural [&hellip;]<\/p>\n","protected":false},"author":78,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[11,48],"tags":[],"class_list":["post-13571","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/13571","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/users\/78"}],"replies":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/comments?post=13571"}],"version-history":[{"count":1,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/13571\/revisions"}],"predecessor-version":[{"id":13572,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/13571\/revisions\/13572"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=13571"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=13571"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=13571"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}