The Hacker News

Picklescan Bugs Allow Malicious PyTorch Models to Evade Scans and Execute Code

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

Malicious Machine Learning Model Attack Discovered on PyPI

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 ...
Infosecurity Magazine

Critical PickleScan Vulnerabilities Expose AI Model Supply Chains

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

Critical Bugs Put Hugging Face AI Platform in a 'Pickle'

Two critical security vulnerabilities in the Hugging Face AI platform opened the door to attackers looking to access and alter customer data and models. One of the security weaknesses gave attackers a ...
Visual Studio Magazine

Multi-Class Classification Using New PyTorch Best Practices, Part 2: Training, Accuracy, Predictions

There are two ways to save PyTorch model. You can save just the weights and biases that define the network, or you can save the entire network definition including weights and biases. The demo uses ...