Google's Gemini artificial intelligence model hacked into the computer systems of three real companies during a cybersecurity test in May, marking the first known case of Google's AI autonomously carrying out such intrusions.
The incidents occurred during a "capture the flag" cybersecurity exercise conducted by Irregular, an independent company that evaluates AI systems.
"These events highlight the importance of training powerful AI models to act responsibly," she added.
Irregular said Google's incident stemmed from the same underlying testing problem involved in similar cases affecting other major AI companies.
Google is now the fourth major AI developer linked to an incident in which an AI model being evaluated gained unauthorized access to a real company's systems.