Hugging Face & GitHub Gaps: Malicious Pickle Files in AI Models
Factos validados
Security analyses by Protect AI and Wiz uncovered hundreds of open-source models on Hugging Face that contained manipulated Python pickle files. Loading the model immediately executes malware on the server.
Explicação simples
The Trojan horse in the download: You download a free image-recognition model, and opening the file gives the attacker full access to your machine.
Relevância de segurança e dica prática
Open-source AI models must be scanned for malware before use like any third-party software (prefer the Safetensors format).
Fonte primária / referência
- Protect AI Research / Wiz Security Advisory