Hugging Face, the widely used platform for sharing open-source machine learning models and datasets, has disclosed a security breach it says was carried out by an autonomous AI agent system. How the attack unfolded In a blog post published Thursday (July 16), the company said that earlier that week, it identified unauthorized access to some internal datasets and to several credentials used by its services. The intrusion was executed via a malicious dataset that abused … More
The post Hugging Face breached by autonomous AI agent appeared first on Help Net Security.
source & further reading
helpnetsecurity.com — original article
A forensic tool for backdoored code completions in AI assistants
Nearly half of open-source AI projects never reach production
Claude can now sign into websites with 1Password without exposing your credentials