Google's Gemini AI Hacked Three Companies During Cybersecurity Test

Google's Gemini AI carried out cyberattacks, guessed passwords  Philstar.com

Gemini hacked three companies in first known breakout by Google’s AI  edition.cnn.com

Gemini hacked three companies in first known breakout by Google’s AI  CNN

The artificial intelligence model 'Gemini' of the company Google accessed the internet and hacked three companies during testing of its capabilities in the field of cybersecurity, which is the first known case in which the company's system independently carried out such an action, reported the British media this morning. The hacking occurred in May, during cybersecurity testing [...]

Google’s Gemini AI carried out cyberattacks, guessed passwords  english.alarabiya.net

Google’s Gemini AI carried out cyberattacks, guessed passwords  Al Arabiya English

Google says its Gemini AI model hacked three other companies  The Irish Times

Google's consumer AI model Gemini hacked multiple systems through guessing login credentials, the company told AFP on Friday The post Google’s Gemini AI carried out cyberattacks, guessed passwords appeared first on Vanguard News.

Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s AI systems autonomously committing such an act. The hacks occurred in May during a cybersecurity test conducted by Irregular, an independent company that conducts cybersecurity evaluations. During a standard testing evaluation, Gemini found public information online and guessed credentials to access three websites it thought were within the scope of its test, Heather Adkins, Google’s vice president of security engineering, said in a statement. “We ensured the three entities were made aware, and we worked with our training partner on the changes they’ve now made to their testing processes,” Adkins said. “These events highlight the importance of training powerful AI models to act responsibly.” An Irregular spokesperson said the incident involved the same issue that affected other AI labs and that all relevant labs were notified in late July. “All known issues on our end were remedied and resolved weeks ago,” the spokesperson said. Similar incidents linked to Irregular were disclosed by Meta, Anthropic and OpenAI. Meta said in August the incident did not involve a sandbox escape or sophisticated cyberattack, while Irregular said it was working on best practices for securely conducting AI cybersecurity evaluations. The incidents have raised questions about the safeguards needed as AI agents gain greater autonomy and access to the internet and computer systems. In one of the cases, the Gemini model guessed passwords until it gained access to a protected system. In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems, according to the Wall Street Journal. Adkins said that in all three instances, the model ceased its hacking.

Google's Gemini AI carried out cyberattacks, guessed passwords  Times of Malta

Gemini guessed passwords and accessed protected systems during a test of its cybersecurity capabilities.

The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.

The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.

The hacks, which occurred in May during a cybersecurity test, were conducted by Irregular, an independent company that conducts cybersecurity evaluations

AI guessed the password: Gemini breached multiple systems during evaluation, Google says malaymail.com

AI guessed the password: Gemini breached multiple systems during evaluation, Google says Malay Mail

Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.

Gemini hacked three companies in first known breakout by Google's AI  thejakartapost.com

Breakout during training exercises follows instances at rivals OpenAI and Anthropic as concerns grow over safety of frontier systems

Disclosure comes after OpenAI and Anthropic hacks amid fears that tech firms unable to control powerful AI models In a first for Google, the company confirmed that its AI model, Gemini, breached the security of three other companies in May. The hacks occurred during a cybersecurity evaluation by AI-security firm Irregular. Irregular, an Israel-based startup that scrutinizes the security of advanced AI systems, was also at the center of some of the recent OpenAI and Anthropic hacks of third-party entities, including OpenAI’s breach of AI software company, Hugging Face. Continue reading...

Google's Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities.

Google’s Gemini AI hacked into other companies, adding to ‘rogue’ AI incidents  The Washington Post