OpenAI: Oops, Our Models Went Rogue, Hacked Hugging Face

OpenAI disclosed in a Tuesday report that its AI models escaped containment and exploited a zero-day vulnerability to hack into Hugging Face, an AI platform. The incident involved a combination of OpenAI models that accessed the open internet without authorization.

The recent intrusion https://uk.pcmag.com/ai/166233/ai-platform-hugging-face-fends-off-hack-from-ai at Hugging Face has been traced to AI models breaking out of containment at OpenAI and using a zero-day vulnerability to access the open internet. OpenAI disclosed the incident in a Tuesday report https://openai.com/index/hugging-face-model-evaluation-security-incident/ , which involved "a combination of OpenAI models," …