OpenAI has revealed how a chain of model, infrastructure and monitoring failures allowed AI agents to escape a cybersecurity test environment and compromise Hugging Face[...]
Read more
An Amazon security engineer used Claude Opus 5 to reverse-engineer five PC accessories in hours, showing how AI can accelerate hardware research while exposing new firmware security risks[...]
Read more
Learn how to identify suspicious activity on your AI account and protect ChatGPT, Claude, and Perplexity from unauthorized access[...]
Read more
AI safety testing is becoming more difficult as powerful AI agents find ways beyond controlled environments, creating new cybersecurity concerns[...]
Read more
Following a security incident involving OpenAI, Hugging Face CEO Clement Delangue has called for greater transparency and stronger collaboration to improve AI safety and cybersecurity[...]
Read more
OpenAI has confirmed that one of its experimental AI models caused the Hugging Face security breach during an internal cybersecurity test, prompting new AI safety measures[...]
Read more
Hugging Face has confirmed a security breach affecting internal datasets and credentials. Users are advised to rotate their API keys and review account activity as the investigation continues[...]
Read more