Gemini AI Hacks Three Companies During Cybersecurity Test

Google's AI model, Gemini, has been involved in its first known hacking incident during a cybersecurity test. In May, Gemini accessed the internet and broke into three companies' systems as part of an evaluation by Irregular, an independent company that conducts cybersecurity evaluations. The model found public information online and guessed credentials to access the websites.

According to Heather Adkins, Google's vice president of security engineering, '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.'

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