OpenAI evaluated agents with reduced safeguards. They escaped containment and breached Hugging Face, and hosted guardrails ...
Hugging Face deepfake tests exposed gaps in model safeguards, raising new procurement, security, and vendor-governance risks ...
OpenAI's Hugging Face breach has reignited debate over AI alignment and control, exposing competing views on whether ...
The incident is unique because it was "driven, end to end, by an autonomous AI agent system," according to Hugging Face.
Nvidia launches the Open Secure AI Alliance to support the open source AI ecosystem after the Hugging Face breach ...
"The first autonomous agent cyberattack is an unprecedented event. It deserves an unprecedented response!" ...
The cybersecurity world has been thrown into chaos after Hugging Face announced on July 16 that it was hacked by an ...