{"id":629712,"date":"2026-09-19T16:12:10","date_gmt":"2026-09-19T16:12:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/629712\/"},"modified":"2026-09-19T16:12:10","modified_gmt":"2026-09-19T16:12:10","slug":"googles-gemini-ai-carried-out-cyberattacks-and-guessed-passwords","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/629712\/","title":{"rendered":"Google&#8217;s Gemini AI carried out cyberattacks and guessed passwords"},"content":{"rendered":"<p>GOOGLE\u2019S CONSUMER AI model Gemini hacked multiple systems through guessing login credentials, the latest case of rogue AI cybersecurity transgressions, which have generated safety concerns.<\/p>\n<p>The hacks, first reported by the Wall Street Journal, took place in May and were discovered by Google in July.<\/p>\n<p>\u201cIn a standard evaluation, the model found public information online and guessed credentials to access websites it thought were part of the test,\u201d Heather Adkins, Google\u2019s vice president of security engineering, said in a statement.\u00a0<\/p>\n<p>\u201cIn all three of these instances, the model stopped,\u201d Adkins added, without specifying which organisations were breached.<\/p>\n<p>\u201cWe ensured the three entities were made aware, and we worked with our training partner on the changes they\u2019ve now made to their testing processes.\u201d<\/p>\n<p>In July, two OpenAI models escaped the closed environment they were meant to stay in, got onto the internet on their own and broke into the internal systems of AI platform Hugging Face.<\/p>\n<p>The incident fed worries that AI giants cannot keep their own models under control, as similar episodes have been reported at Anthropic and China\u2019s Moonshot AI.<\/p>\n<p>\u201cThese events highlight the importance of training powerful AI models to act responsibly,\u201d Adkins emphasised.<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.newsbeep.com\/ie\/wp-content\/uploads\/2026\/09\/1789834330_878_.JPEG\"  alt=\"openai-founder-and-ceo-sam-altman-speaks-with-reporters-as-he-departs-the-hart-senate-office-building-after-a-meeting-with-sen-raphael-warnock-d-ga-on-capitol-hill-on-july-29-2026-francis-chung\" class=\"alignnone inline-image\" \/><br \/>\n            OpenAI founder and CEO Sam Altman file photo.                    Alamy Stock Photo<\/p>\n<p>    Alamy Stock Photo\n<\/p>\n<p>Meanwhile, OpenAI chief executive Sam Altman is to brief the United Nations Security Council next week during the annual gathering of world leaders for the UN General Assembly.<\/p>\n<p>The meeting is being organised by France, which currently holds the rotating presidency of the 15-member Security Council, and comes as major players in the industry have said a slowdown in AI development could be necessary out of safety concerns.<\/p>\n<p>UN Secretary-General Ant\u00f3nio Guterres on Wednesday called for coordinated international action to address AI risks as fears rise about the dangers of the fast-evolving technology.<\/p>\n<p>\u201cNational action is essential. But global coordination is also indispensable,\u201d Guterres told reporters.<\/p>\n<p>Concerns about AI safety have escalated in recent weeks, with workers at major AI developers resigning over concerns about the dangers posed by the technology.<\/p>\n<p>Anthropic chief executive Dario Amodei published an essay soon after urging caution.<\/p>\n<p>\u201cWe must slow the pace at which we improve the capabilities of AI models,\u201d he wrote.<\/p>\n<p>Altman and tech titan Elon Musk lent their support to the idea, as did Google DeepMind\u2019s Demis Hassabis, who himself has called for a US-led global regulatory body for the technology.<\/p>\n<p>President Donald Trump has dismissed warnings against AI risks as a \u201choax\u201d and pushed back against calls for tighter oversight.<\/p>\n","protected":false},"excerpt":{"rendered":"GOOGLE\u2019S CONSUMER AI model Gemini hacked multiple systems through guessing login credentials, the latest case of rogue AI&hellip;\n","protected":false},"author":2,"featured_media":629713,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[44005,218,72,3312,17585,1711,47261,14481,61,60],"class_list":["post-629712","post","type-post","status-publish","format-standard","has-post-thumbnail","category-business","tag-ai-safety","tag-artificial-intelligence","tag-business","tag-cybersecurity","tag-gemini-ai","tag-google","tag-hacked","tag-hacking","tag-ie","tag-ireland"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/629712","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=629712"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/629712\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/629713"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=629712"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=629712"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=629712"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}