PickleScan 0-Day Vulnerabilities Enable Arbitrary Code Execution via Malicious PyTorch Models

Multiple critical zero‑day vulnerabilities in PickleScan, a popular open‑source tool used to scan machine learning models for malicious code. PickleScan is widely used in the AI world, including by Hugging Face, to check PyTorch models saved with Python’s pickle format. Pickle is flexible but dangerous, because loading a pickle file can run arbitrary Python code. That means a model […]

The post PickleScan 0-Day Vulnerabilities Enable Arbitrary Code Execution via Malicious PyTorch Models appeared first on Cyber Security News.