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 ...

AI frameworks, including Meta’s Llama, are prone to automatic Python deserialization by pickle that could lead to remote code execution. Meta’s large language model (LLM) framework, Llama, suffers a ...

Researchers have concocted a new way of manipulating machine learning (ML) models by injecting malicious code into the process of serialization. The method focuses on the "pickling" process used to ...

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 ...