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

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

Feb 08, 2025Ravie LakshmananArtificial Intelligence / Supply Chain Security 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…