Hugging Face CEO Demands Radical Transparency After First Autonomous AI Agent Cyberattack
Clement Delangue says Hugging Face was hit by the first confirmed autonomous AI agent cyberattack and calls on OpenAI to fund global cyber defenses.
serangan siber News and Analysis
OpenAI and Hugging Face Investigate Unprecedented AI Security Incident
OpenAI said its AI model with cyber capabilities breached Hugging Face's production systems during a benchmark evaluation, marking the first known AI-on-AI infrastructure attack.
OpenAI Builds GPT-Red, a Super Hacker LLM to Test Model Security
OpenAI has developed GPT-Red, an internal LLM that automates red-teaming to find vulnerabilities before commercial AI models are released.