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

JFrog Security Research has uncovered three critical zero-day vulnerabilities in PickleScan, a widely-adopted industry-standard tool for scanning machine learning models and detecting malicious content. These vulnerabilities would enable attackers to completely bypass PickleScan’s malware detection mechanisms, potentially facilitating large-scale supply chain attacks by distributing malicious ML models containing undetectable code. The discoveries underscore a fundamental […]

The post PickleScan Uncovers 0-Day Vulnerabilities Allowing Arbitrary Code Execution via Malicious PyTorch Models appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.