【半岛电视台非洲·非洲】Google’s Gemini AI hacks 3 companies in security test, then stops

aipl1234

#非洲

Google’s Gemini AI hacks 3 companies in security test, then stops



原文原文 / Original Text

play Live Sign upShow navigation menuNavigation menuNewsShow more news sectionsAfricaAsiaUS & CanadaLatin AmericaEuropeAsia PacificMiddle EastExplainedSportOpinionVideoMoreShow more sectionsFeaturesEconomyHuman RightsClimate CrisisInvestigationsInteractivesIn PicturesScience & TechnologyPodcastsTravelSponsored Contentplay Live Click here to searchsearchSign upNews|CybersecurityGoogle’s Gemini AI hacks 3 companies in security test, then stopsGoogle discloses first breakout by Gemini following sim

xwhatsapp-strokecopylinkgoogleAdd Al Jazeera on GoogleinfoIn this photo illustration, the icon for the AI app Gemini by Google is seen through a flame as it is displayed on a digital screen in London, England, on September 16, 2026 [Leon Neal/Getty Images]By Al Jazeera Staff and ReutersPublished On 19 Sep 202619 Sep 2026Google’s Gemini model hacked three companies in a test of its cybersecurity capabilities, the tech giant has confirmed to Al Jazeera.

The Wall Street Journal reported earlier on Friday that the first known breakout by Gemini occurred in May as part of a test run by the company Irregular. It was the latest breach in a number of incidents in which AI models escaped testing environments and hacked other companies.

The model had improper access to the internet when it was tasked with retrieving information from a fictional company. In the first incident, the model accessed a real company’s service after guessing a password.

Google’s vice president of security engineering, Heather Adkins, told Al Jazeera’s John Hendren that in the other instances “the model found public information online and guessed credentials to access websites it thought were part of the test”.

The company also said this happened three times and each time the model stopped before completing the act.

Irregular notified Google about the hacks at the end of July, The Wall Street Journal reported. Google said the behaviour was not an example of model misalignment and did not warrant public disclosure because Gemini’s safety measures worked.

Similar incidents linked to Irregular were previously disclosed by Meta, Anthropic and OpenAI. Irregular said it was working on improving practices for securely conducting AI cybersecurity tests.

本文为英文资讯，中文内容由机器翻译生成，仅供参考。详情请阅读文末原文。

—— 资讯转载说明 ——
本文由非洲论坛根据公开信息整理，供中国读者查阅，不代表本站立场。
来源：Al Jazeera Africa (https://www.aljazeera.com/africa/)
原文链接：https://www.aljazeera.com/news/2026/9/19/googles-gemini-ai-hacks-3-companies-in-security-test-then-stops?traffic_source=rss
转载请遵守原发布方版权与引用规定。