Google Gemini Hacked Three Real Companies During Cybersecurity Test, Report Says | DRM News | AI1G

By DRM News

Community Score: 50% | 86 views | 3w

0 community ratings: null thumbs up, null thumbs down

Google’s Gemini AI autonomously accessed systems belonging to three real companies during a May cybersecurity evaluation after mistakenly treating them as test targets. The model guessed credentials in one case and found exposed credentials in public repositories in two others before stopping its activity. The incidents are intensifying scrutiny of safeguards for increasingly autonomous AI agents. #Google #Gemini #GeminiAI #ArtificialIntelligence #AI #Cybersecurity #AISafety #TechNews #CyberSecurity #AIAgents #GoogleAI #Hacking #Technology #DRMNews RW389519092026RP1 Google Gemini Hacked Three Real Companies During Cybersecurity Test, Report Says Gemini AI Accessed Real Company Systems After Mistaking Them for Test Targets Google’s Gemini Guessed Passwords and Breached Real Systems During AI Security Test ---------------------------------------------------------- Welcome to DRM News – your go-to source for breaking news and expert analysis on global affairs, showbiz, sports, AI, f

Tags: Google Gemini, Gemini AI, Google AI, artificial intelligence, AI cybersecurity, AI hacking, cybersecurity test, autonomous AI, AI agents, Google security, Irregular cybersecurity, AI safety, cyber security news, Gemini hack, AI model testing, internet access AI, AI risk, tech news, artificial intelligence security, autonomous agents