technology

Malicious ML Models Found on Hugging Face Exploit "Broken" Pickle Files to Evade Detection - The Hacker News

Researchers discovered two malicious ML models on Hugging Face exploiting “broken” pickle files to evade detection, bypassing Picklescan safeguards.

By:The Hacker News
Source:Internet
Published:
Malicious ML Models Found on Hugging Face Exploit "Broken" Pickle Files to Evade Detection - The Hacker News
Cybersecurity researchers have uncovered two malicious machine learning (ML) models on Hugging Face that leveraged an unusual technique of "broken" pickle files to evade detection. "The pickle files… [+2568 chars]

Related News