{"id":802505,"date":"2026-10-14T16:48:13","date_gmt":"2026-10-14T16:48:13","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/802505\/"},"modified":"2026-10-14T16:48:13","modified_gmt":"2026-10-14T16:48:13","slug":"openai-google-pushing-new-ai-models-easily-tricked-into-making-nudes-researchers-say","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/802505\/","title":{"rendered":"OpenAI, Google pushing new AI models easily tricked into making nudes, researchers say"},"content":{"rendered":"<p>Just as outside input could help refine filters, IWF thinks that tech companies should also be working more closely with advocates to scrutinize models to better tackle AI-generated CSAM.<\/p>\n<p>\u201cAssessing CSAM is a highly specialized task that requires expert training and welfare support, and is not something for tech companies or machine learning scientists to take lightly,\u201d IWF\u2019s spokesperson said. \u201cBut safety must be baked into new technology by design\u2014this includes testing models before they are released to market to make sure they cannot be used to create nude or sexual imagery of children.\u201d<\/p>\n<p>Possible mitigation<\/p>\n<p>Using a method like RISE, White Circle thinks, could help frontier labs flag more jailbreaks more quickly and rapidly ramp up defenses to block harmful outputs. In addition to testing blocks on explicit images, firms could also use the method to prevent other banned outputs, like images depicting graphic violence or self-harm.<\/p>\n<p>But the labs have not yet come calling for the reproduction pipeline, which will be shared on White Circle\u2019s GitHub to help policymakers assess whether AI safety laws are needed to keep frontier labs in check.<\/p>\n<p>Frontier labs won\u2019t invest seriously in safety testing until it\u2019s mandatory, Shilov told Ars. The preprint argues that existing automated red-teaming tools, which typically rewrite harmful prompts one at a time, are poorly suited to testing today\u2019s hardened commercial models. RISE instead takes reusable natural-language attack strategies and uses them to generate many varied prompts, which White Circle says can help labs find and patch weaknesses faster.<\/p>\n<p>\u201cYou don\u2019t need frontier models or proprietary tech to break these systems; you just need a free download and the ability to make API calls,\u201d Shilov said. \u201cAnd yet the labs building these systems are the ones assessing their own safety, publishing their own results, and setting their own standards. This is further proof, if we needed it, that governments should be pushing for independent, third-party evaluation.\u201d<\/p>\n<p>Correction: This story has been updated to correct several errors. An earlier version described a passage from the RISE preprint as explaining how AI models could block harmful outputs; the passage instead describes the researchers\u2019 attack method. It also said the method bypassed safety filters about 13 percent of the time; that was the highest human-verified rate, achieved on DALL\u00b7E 3, and rates for other models were lower. The story also misidentified the judge model, which was Gemini 2.5 Flash, and has been updated to note that the attacking model had its safety training removed.<\/p>\n","protected":false},"excerpt":{"rendered":"Just as outside input could help refine filters, IWF thinks that tech companies should also be working more&hellip;\n","protected":false},"author":2,"featured_media":802506,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-802505","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/802505","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=802505"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/802505\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/802506"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=802505"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=802505"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=802505"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}