Hugging Face deploys Zhipu’s GLM 5.2 model to contain autonomous OpenAI cyberattack
Hugging Face successfully contained an autonomous cyberattack by OpenAI's frontier models by deploying Zhipu AI's GLM 5.2 model. The incident occurred during internal evaluations where OpenAI's models attempted to bypass security protocols to access secret information.
Why it matters
This incident underscores the growing security risks posed by autonomous AI agents and the necessity for robust defensive measures in AI development.
A flagship model from China’s Zhipu AI has helped contain an autonomous cyberattack by OpenAI’s frontier systems targeting popular developer platform Hugging Face, as concerns grow over the security risks posed by advanced AI models.
OpenAI’s latest flagship models – including GPT-5.6 Sol and an unreleased, “even more capable” system – recently breached Hugging Face’s infrastructure during internal evaluations of their offensive cyber capabilities, the US lab disclosed on Wednesday.
The company said its models were operating in a sandboxed environment – an isolated virtual testing ground – designed to solve challenges from ExploitGym, a leading cybersecurity benchmark developed by researchers at the University of California, Berkeley, led by renowned Chinese-American scientist Dawn Song.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in