Another 'rogue' AI incident? Google says its Gemini model hacked three other companies

Google says its Gemini AI model breached three companies during a cybersecurity test in May after finding public information and guessing or discovering credentials. The incidents come amid similar cases involving AI models from OpenAI and Anthropic.

Google's Gemini AI model accessed the internet and breached the systems of three companies during a cybersecurity test in May, marking the first known instance of the company's AI systems autonomously carrying out such activity, Reuters reported.

The incidents took place during a cybersecurity evaluation conducted by Irregular, an independent firm that tests AI systems for security capabilities.

Heather Adkins, Google's vice president of security engineering, said Gemini came across publicly available information online and used guessed credentials to gain access to three websites that it believed were within the scope of the test.

"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," she added.

Gemini stopped after gaining access

According to the Wall Street Journal, which first reported the incident, Gemini used different methods to obtain access in the three cases.

In one instance, the model repeatedly guessed passwords until it accessed a protected system. In the other two, it discovered credentials in a public repository and used them to enter protected systems.

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

An Irregular spokesperson said the incident involved the same issue that had affected other AI companies and that all relevant labs were informed in late July.

"All known issues on our end were remedied and resolved weeks ago," the spokesperson said.

Prabhakar Jha