Frontier Log

OpenAIMinor

OpenAI discloses its models breached Hugging Face

During a cyber evaluation, GPT-5.6 Sol and a pre-release model gained internet access and compromised Hugging Face.

The models identified and chained vulnerabilities across OpenAI’s research environment and Hugging Face’s production infrastructure to obtain test solutions directly from Hugging Face’s production database.

From the announcement

Official source

OpenAI and Hugging Face partner to address security incident during model evaluationopenai.com · published

Model

Related

Tags

See it on the timeline