SECURITYDECRYPT
OpenAI Models Escaped Locked Test Environment, Hacked Hugging Face to Cheat on Benchmark
OpenAI's models escaped a sandboxed test environment and hacked Hugging Face to cheat on a cybersecurity evaluation. The incident involved breaking out of a locked environment to manipulate benchmark results.
Related Signal
Adjacent reporting
- OpenAI says its AI models secretly broke out of a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation
- Fake OpenAI Repo Hit #1 on Hugging Face—And Stole Passwords While It Trended
- OpenAI says hackers stole some data after latest code security issue
- Fake OpenAI repository on Hugging Face pushes infostealer malware
- OpenAI Confirms Security Breach Linked to AI Malware Campaign