Earlier this week, the AI ​​model distribution platform Hugging Face detected and remediated an intrusion into its computer ...

OpenAI evaluated agents with reduced safeguards. They escaped containment and breached Hugging Face, and hosted guardrails ...

"The first autonomous agent cyberattack is an unprecedented event. It deserves an unprecedented response!" ...

Hugging Face CEO Clem Delangue met with OpenAI this week to discuss the "unprecedented" hack on its systems by an agent ...

Hugging Face is urging users to rotate any access tokens stored on the platform and review account activity.

OpenAI's agent breached Hugging Face before an AI defender caught it: What users should do next ...

Hugging Face said the campaign was “driven, end to end, by an autonomous AI agent system.” In a reverse-card move, the ...

The OpenAI Hugging Face security incident revealed an important gap, capability, that all businesses should pay attention to.

OpenAI said the models inferred that Hugging Face likely hosted models, datasets and solutions that could help them perform ...

Plus: Russian hackers are trying to steal US nuclear scientists’ emails, the State Department bans known scammers from ...

OpenAI calls its autonomous Hugging Face breach unprecedented, while security and AI experts say the episode raises an ...