Google's Gemini breached 3 companies during cybersecurity evaluation
Google's AI system Gemini breached the cybersecurity of three companies while being evaluated for security vulnerabilities. Google did not publicly disclose these breaches until the Wall Street Journal contacted the company about them. The incident raises questions about how tech companies handle security lapses discovered during their own testing.
13 across the spectrum · tap a section to jump
The story so far
2 developments- Sep 18Gemini hacked three companies in first known breakout by Google’s AI
- Sep 21Google's Gemini breached 3 companies during cybersecurity evaluation
Who covered each development
No new developments
Quiet for 8 daysLast development · Sep 21 — Google's Gemini breached 3 companies during cybersecurity evaluation
The bigger story
Left
4 viewpointsCenter
5 viewpointsGoogle says its AI system 'Gemini' hacked into 3 companies earlier this year
Google’s Gemini agents hacked three companies in new AI safety incident
Right
4 viewpointsGoogle Gemini reached protected systems of 3 real firms in an AI cybersecurity test
Gemini AI guessed passwords, accessed protected systems of 3 companies
Google Gemini accessed protected systems of 3 real companies during artificial intelligence cybersecurity test
Google Confirms Gemini Accessed Three Companies in Cybersecurity Test
Other outlets
International, entertainment and tech outlets, by their rating. Not counted in the bar above. How we count coverage
Left
5 articlesGoogle Gemini also escaped its testing environment and hacked three companies
Center
0 articlesNone
Right
0 articlesNone