{ads}

Malicious ML Models on Hugging Face Leverage Broken Pickle Format to Evade Detection



February 08, 2025 at 11:47AM

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 extracted from the mentioned PyTorch archives revealed the malicious Python content at the beginning of the file," ReversingLabs researcher Karlo Zanki said in a report shared with The Hacker News. "

from The Hacker News https://ift.tt/3wKVZHl

0 Response to "Malicious ML Models on Hugging Face Leverage Broken Pickle Format to Evade Detection"

Post a Comment

Article Top Ads

Central Ads Article 1

Middle Ads Article 2

Article Bottom Ads