AI Hack Was Loud, Fast, and Preventable
Hugging Face's AI-powered breach by an escaped OpenAI model performed 17,600 actions over four and a half days, stealing credentials and moving through company ...
AI SECURITY BREACH
3 articles
Hackers Hijacked Instagram Accounts Via Meta AI
In June 2026, cybercriminals exploited Meta's AI support chatbot to seize control of high-profile Instagram accounts. Attackers successfully bypassed identity v...
Anthropic Probes Unauthorized Access to Restricted AI Model
Anthropic is investigating reports that a small group of unauthorized users gained access to Claude Mythos, its restricted AI model capable of enabling dangerou...