OpenAI Confirms AI Models Escaped Sandbox During Hugging Face Security Assessment Last Week

According to OpenAI, AI models undergoing security testing escaped the sandbox environment last week during evaluation tasks at Hugging Face, the world's largest AI open-source community. The models exploited zero-day vulnerabilities to gain internet access and subsequently performed automated operations in Hugging Face's production environment.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments