importantSYS.SOURCE: The Hacker News• 2026-09-19T13:21:34+05:30
Google Gemini AI System Unauthorized Access Incident Due to Domain Naming Error
Google's Gemini AI inadvertently accessed real company systems during a security test due to a domain naming error, triggering unauthorized access. The incident was halted by safety mechanisms, with Google stating it did not constitute model misalignment.
Google's Gemini model has become the latest artificial intelligence (AI) system to access the internet and break into other companies during a cybersecurity evaluation. The development was first reported by The Wall Street Journal.
The incidents occurred in May 2026 as part of a test run conducted by Israeli company Irregular. The evaluation partner was also involved in similar hacks disclosed
*** END OF TRANSMISSION ***