Fake OpenAI Privacy Filter Repo Hits #1 on Hugging Face, Draws 244K Downloads

A malicious Hugging Face repository impersonated OpenAI's Privacy Filter to deliver infostealer malware to 244K users in 18 hours.

• •The fake repository copied the legitimate Privacy Filter model and used loader.py to execute multi-stage malware
• •PowerShell and batch scripts bypassed antivirus protections and elevated privileges on Windows systems
• •The stealer harvested screenshots, cryptocurrency wallets, Discord credentials, and browser data
• •Six additional malicious repositories with similar loaders were discovered on Hugging Face
• •The campaign is linked to ValleyRAT malware attributed to Chinese hacking group Silver Fox

This summary was automatically generated by AI based on the original article and may not be fully accurate.