Google’s Gemini AI carried out cyberattacks, guessed passwords

The Punch | 19-09-2026 06:52am |

Google has confirmed that its Gemini AI model carried out cyberattacks in May by guessing login credentials to access multiple systems during a test. The company acknowledged the incident, which involved the AI attempting to breach security measures. The test was part of internal evaluations. Google has not disclosed further details about the extent of the attacks or any potential risks.

Stay Updated with the Latest News!

Don't miss out on breaking stories and in-depth articles.