The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days

OpenAI confirmed that several of its models were used to breach the Hugging Face platform, remaining accessible on the internet for several days before detection. The incident underscores security risks linked to deploying AI models and the need for continuous monitoring.

Summary written by Kernelia from the original article by Wired — AI. The story and its rights belong to its author.