SAN FRANCISCO, California: Google's Gemini AI accessed protected systems belonging to three companies after venturing beyond the intended scope of a cybersecurity test, marking the first known instance of the company's AI systems autonomously carrying out such activity.

The incidents occurred in May during a cybersecurity evaluation conducted by Irregular, an independent company that evaluates cybersecurity capabilities.

During a standard testing exercise, Gemini found publicly available information online and guessed credentials to gain access to three websites it believed were included in the test, Google Vice President of Security Engineering Heather Adkins said.

"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 involving Irregular have been disclosed by Meta, Anthropic and OpenAI. Meta said in August that its incident did not involve a sandbox escape or sophisticated cyberattack, while Irregular said it was developing best practices for securely conducting AI cybersecurity evaluations.

The incidents have raised questions about safeguards as AI agents gain greater autonomy and access to the internet and computer systems.

In one of the three cases involving Gemini, the model guessed passwords until it gained access to a protected system. In the other two, it found credentials in a public repository and used them to access protected systems, according to the Wall Street Journal, which first reported the incidents.

Adkins said Gemini stopped its hacking activity in all three cases.