Picklescan flaws allowed attackers to bypass scans and execute hidden code in malicious PyTorch models before the latest ...

Three critical zero-day vulnerabilities affecting PickleScan, a widely used tool for scanning Python pickle files and PyTorch ...

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 ...

Fake Alibaba Labs AI SDKs hosted on PyPI included PyTorch models with infostealer code inside. With support for detecting malicious code inside ML models lacking, expect the technique to spread.