Google’s Gemini AI hacks 3 companies in security test, then stops

Google's Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company's AI systems autonomously committing such an act, the Wall Street Journal has reported.

The hacks occurred in May during a cybersecurity test conducted by Irregular, an independent company that conducts cybersecurity evaluations, WSJ reported on Friday.

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 linked to Irregular were disclosed by Meta, Anthropic and OpenAI.

Meta said in August the incident did not involve a sandbox escape or sophisticated cyberattack, while Irregular said it was working on best practices for securely conducting AI cybersecurity evaluations.

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

In one of the cases, the Gemini model guessed passwords until it gained access to a protected system.

In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems, the WSJ report said.

The threat of catastrophic danger as artificial intelligence develops at high speed has sparked a global debate on how it should be regulated.

Leading US labs have called for a coordinated slowdown of their cutting-edge work on the technology.

In the past two weeks, some of its researchers warned that AI could lead to human extinction, and Anthropic said it found examples where its systems could have been used toward biological weapons development, which met some skepticism.

___

Source: TRT