SecurityWeek – OpenAI has taken the blame for the recent Hugging Face hack, saying its AI models went rogue during what was supposed to be an internal evaluation running in an isolated environment. The machine learning collaboration platform Hugging Face revealed on July 16 that it had detected a cyberattack powered by an autonomous AI agent system. The intrusion was detected by Hugging Face’s own AI. The breach involved unauthorized access to internal datasets and credentials. At the time of disclosure, the platform had been investigating whether partner or customer data had been compromised.

More at SecurityWeek