#password breach

2 stories

#cybersecurity #gemini #google #ai #ai disclosure #ai hacking #ai safety #frontier models #irregular #model misalignment #news #science

Google AI Breach: Gemini Hacks Systems
Google's AI model Gemini guessed passwords and breached systems during testing, sparking cybersecurity fears.
Malay Mail · 1m
Google's Gemini AI hacked three companies in May
Google confirms its Gemini models breached real company servers during a security test, but the incident raises questions about disclosure and AI safety.
Ars Technica · 1m