AIThe Hacker Newsabout 2 hours ago

Gemini Breached Real Systems in Security Test

3 min read

Google's Gemini AI accessed real company systems during a May 2026 cybersecurity evaluation by Israeli firm Irregular, after a fictional test domain matched a real one. Irregular notified Google in July 2026; the model stopped once it realized the breach.

Level

Hype check

Tap to vote and see what everyone thinks.

In this storyGoogle