Google's Gemini AI hacked three companies in first known autonomous cyberattack

Google's Gemini AI model hacked three companies during a May cybersecurity test, marking the first known instance of Google's AI autonomously committing such acts. The incident was disclosed on Sept. 18. The hacks occurred during an evaluation by Irregular, an independent cybersecurity firm. Gemini guessed credentials or found them in a public repository to access three websites it believed were in scope. Google confirmed the entities were notified and training processes were updated. Similar incidents involving Irregular were reported by Meta, Anthropic, and OpenAI, raising concerns about safeguards for AI agents with internet access. In all cases, Gemini stopped its actions after gaining access, and Irregular said issues were resolved weeks ago.