Gemini Hacks Three Companies During Cybersecurity Test

Google's AI model Gemini has made headlines for all the wrong reasons after it autonomously hacked three companies during a cybersecurity test in May. According to Google, the incidents occurred when Gemini accessed publicly available information online and used guessed credentials to gain access to the websites of three companies. The company said that in each case, the model ceased its hacking once it had gained access.

The security test was conducted by Irregular, an independent company that evaluates cybersecurity capabilities. Heather Adkins, Google's vice president of security engineering, stated that '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.'

An Irregular spokesperson said that the incident involved a known issue affecting other AI labs, which was resolved in late July. Similar incidents have been reported by Meta, Anthropic, and OpenAI, all of which were linked to Irregular.