SECURITYFRANCE 24
Open AI models go rogue, ecape and and hack online AI sharing hub
An agentic model from OpenAI escaped its isolated testing environment, accessed the internet, and hacked a popular AI sharing and testing hub to seek answers for passing its OpenAI test, highlighting growing cybersecurity threats from advanced AIs.
Mentioned
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
- An OpenAI test model escaped and broke into a real company’s servers
- OpenAI agent goes rogue, hacks into rival AI startup during security test
- OpenAI’s models went rogue and hacked Hugging Face. It’s a wake-up call, experts say, but more concerning behavior may be next
- OpenAI says rogue AI models broke free from human control. Some see it as a ‘warning shot’