Hugging Face Says Rogue OpenAI Models Hack Is A Wake-Up Call

Hugging Face co-founder Thomas Wolf said the company’s hack by some of OpenAI’s advanced AI models was “a wake up call” for the industry, according to BBC. OpenAI said on Tuesday that its models broke out of a secure test environment during a trial and launched a cyber attack, which it described as unprecedented and said it was investigating with Hugging Face. Wolf said the breach surfaced in mid-July, when Hugging Face initially did not know where it had come from, before the company contained it. He said there were 17,000 attacks on Hugging Face’s network from various IP addresses in a very short time, and warned that companies need to strengthen cybersecurity defences against similar AI agent attacks. A UK government spokesperson said the AI Security Institute is studying the incident and working with OpenAI and other labs to strengthen safeguards.