The popular Python Pickle serialization format, which is common for distributing AI models, offers ways for attackers to inject malicious code that will be executed on computers when loading models ...

A new campaign exploiting machine learning (ML) models via the Python Package Index (PyPI) has been observed by cybersecurity researchers. ReversingLabs said threat actors are using the Pickle file ...

Three critical zero-day vulnerabilities affecting PickleScan, a widely used tool for scanning Python pickle files and PyTorch models, have been uncovered by cybersecurity researchers. The flaws, all ...