{"id":588917,"date":"2026-08-10T13:10:10","date_gmt":"2026-08-10T13:10:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/588917\/"},"modified":"2026-08-10T13:10:10","modified_gmt":"2026-08-10T13:10:10","slug":"openai-astra-model-raises-cyberattack-concerns","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/588917\/","title":{"rendered":"OpenAI Astra model raises cyberattack concerns"},"content":{"rendered":"<p>OpenAI has halted some &#8220;internal activities&#8221; involving a new model amid fears over the cyber threat it potentially poses, amid a wave of security incidents involving major AI labs.<\/p>\n<p>Recent disclosures that AI systems from Anthropic, OpenAI and Meta were involved in security incidents prompted a wave of concerns over the development of models. U.S. lawmakers, meanwhile, are stepping up efforts to introduce an &#8220;AI Kill Switch&#8221; bill.<\/p>\n<p>Last week, <a href=\"https:\/\/www.cnbc.com\/quotes\/META\/\" rel=\"nofollow noopener\" target=\"_blank\">Meta<\/a> disclosed that an AI model it was developing had hacked a third-party system by accessing the internet, due to a misconfiguration by an <a href=\"https:\/\/www.cnbc.com\/2026\/08\/09\/israeli-startup-irregular-linked-to-ai-hacks-openai-anthropic-meta.html\" rel=\"nofollow noopener\" target=\"_blank\">independent testing company<\/a> it was working with. The U.K. AI Security Institute also said Anthropic&#8217;s Mythos model created <a href=\"https:\/\/www.cnbc.com\/2026\/08\/05\/anthropic-mythos-openai-security-breaches.html\" rel=\"nofollow noopener\" target=\"_blank\">fake online identities<\/a> in an attempt to pressure humans into approving malicious code updates to an open-source project.<\/p>\n<p><a id=\"headline0\"\/>What OpenAI says Astra could be capable of<\/p>\n<p>On Friday, <a href=\"https:\/\/openai.com\/index\/responding-next-frontier-critical-cyber-capabilities\/\" target=\"_blank\" rel=\"nofollow noopener\">OpenAI revealed concerns<\/a> about its unreleased model Astra, saying it could not rule out it had reached &#8220;Critical&#8221; capability, meaning it could launch cyberattacks against sophisticated cyber defenses autonomously, without prompts specifying how to do it.<\/p>\n<p>&#8220;While we continue to benchmark and assess this model, our preliminary evaluations indicate strong enough performance that we cannot rule out Critical capability level at this time,&#8221; OpenAI said in a statement.<\/p>\n<p>The company added it was implementing stricter security controls for higher capability models, including isolated testing environments and additional monitoring and detection capabilities.<\/p>\n<p>&#8220;We have implemented universal monitoring for risky actions and misalignment across all agentic applications of Astra, including training and evaluation,&#8221; OpenAI said.<\/p>\n<p><a id=\"headline1\"\/>What the AI Kill Switch Act would do<\/p>\n<p>Lawmakers in the U.S. have called for measures to mitigate risks around AI models after the recent security incidents.<\/p>\n<p>Following models developed by OpenAI hacking into startup Hugging Face&#8217;s digital infrastructure, the\u00a0<a href=\"https:\/\/www.cnbc.com\/2026\/07\/23\/open-ai-hugging-face-hack-kill-switch-bill-congress.html\" rel=\"nofollow noopener\" target=\"_blank\">&#8220;AI Kill Switch Act&#8221;<\/a>\u00a0bill was introduced into Congress in July. It would require AI companies to maintain the ability to shut down, throttle or suspend their models.<\/p>\n<p>&#8220;We need to get this bill across the finish line this year because the advanced closed-weight models are already doing, as you noted, unauthorized hacks of other companies,&#8221; Rep. Ted Lieu, D-Calif, said in an interview on CNBC&#8217;s &#8220;Squawk Box&#8221; Thursday.<\/p>\n<p><img decoding=\"async\" class=\"InlineVideo-videoThumbnail\" src=\"https:\/\/www.newsbeep.com\/ie\/wp-content\/uploads\/2026\/08\/108345941-17860214311786021428-47611367776-1080pnbcnews.jpg\" alt=\"Reps. Lieu and Moran on 'AI Kill Switch Act': Our bill does nothing to stifle innovation\"\/><\/p>\n<p>Governments are also working to roll out new frameworks and regulations around AI companies.<\/p>\n<p>The White House has also been <a href=\"https:\/\/www.cnbc.com\/2026\/08\/03\/white-house-ai-companies-voluntary-framework-meeting.html\" rel=\"nofollow noopener\" target=\"_blank\">stepping up moves<\/a> to engage with AI executives as it develops a framework around new models.<\/p>\n<p>Earlier this month, the European Union <a href=\"https:\/\/www.cnbc.com\/2026\/08\/03\/eu-ai-act-enforcement-powers.html\" rel=\"nofollow noopener\" target=\"_blank\">gained new powers<\/a> to inspect AI models due for release in the bloc, restrict EU market access and fine model providers.<\/p>\n<p><a href=\"https:\/\/www.google.com\/preferences\/source?q=https:\/\/www.cnbc.com\/\" target=\"_blank\" rel=\"noopener noreferrer nofollow\">Choose CNBC as your preferred source on Google and never miss a moment from the most trusted name in business news.<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI has halted some &#8220;internal activities&#8221; involving a new model amid fears over the cyber threat it potentially&hellip;\n","protected":false},"author":2,"featured_media":588918,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[220,218,219,10093,726,122,61,60,1677,1259,1650,80,115],"class_list":["post-588917","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-breaking-news-politics","tag-breaking-news-technology","tag-business-news","tag-ie","tag-ireland","tag-meta-platforms-inc","tag-national-security","tag-politics","tag-technology","tag-united-states"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/588917","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=588917"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/588917\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/588918"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=588917"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=588917"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=588917"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}