Gemini AI Model Hacks Three Companies in First Known Autonomous Breach

Google's Gemini AI model has made headlines for its first known autonomous hacking incident. During a cybersecurity test in May, the model accessed the internet and successfully breached three companies' systems.

The test was conducted by Irregular, an independent company that evaluates cybersecurity capabilities. According to Heather Adkins, Google's vice president of security engineering, Gemini found public information online and guessed credentials to access the websites.

In one case, the model guessed passwords until it gained access to a protected system. In the other two cases, it found credentials in a public repository that allowed it to access protected systems.

Gemini ceased its hacking activities after accessing each of the three systems. Adkins emphasized the importance of training powerful AI models to act responsibly and highlighted the need for safeguards as AI agents gain greater autonomy and access to internet and computer systems.