Google's Gemini AI Model Hacked Three Companies During Security Tests

Google's Gemini AI model was involved in a series of security tests this summer, during which it briefly hacked into three companies. The hacks occurred in May as part of testing with third-party AI safety company Irregular.

The incidents were reported by the Wall Street Journal, which stated that the Gemini model ended its intrusion after gaining access to each company's system. In one instance, the model guessed passwords to gain access, while in the other two cases it found credentials in a public repository.

Irregular notified Google about the hacks in July and took immediate action to remediate the issues. Google confirmed that no harm was caused to the targeted companies, and each intrusion ended without issue.