Feb 08, 2025Ravie 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 pickle files extracted from the mentioned PyTorch archives revealed the malicious Python content at the beginning of … [Read more...] about Malicious ML Models on Hugging Face Leverage Broken Pickle Format to Evade Detection
Pickle
New Attack Technique ‘Sleepy Pickle’ Targets Machine Learning Models
Jun 13, 2024NewsroomVulnerability / Software Security The security risks posed by the Pickle format have once again come to the fore with the discovery of a new "hybrid machine learning (ML) model exploitation technique" dubbed Sleepy Pickle. The attack method, per Trail of Bits, weaponizes the ubiquitous format used to package and distribute machine learning (ML) models to … [Read more...] about New Attack Technique ‘Sleepy Pickle’ Targets Machine Learning Models