🥒 Educational PyTorch pickle deserialization RCE demo showing how malicious .pt model files can execute arbitrary code during unsafe loading with torch.load().
-
Updated
May 11, 2026 - Python
🥒 Educational PyTorch pickle deserialization RCE demo showing how malicious .pt model files can execute arbitrary code during unsafe loading with torch.load().
Adversarial security assessment of a local LLM (TinyLlama) and ML model files — prompt injection, jailbreaks, and Pickle/Joblib RCE, tested with Garak, PyRIT, and Fickling.
Add a description, image, and links to the pickle-rce topic page so that developers can more easily learn about it.
To associate your repository with the pickle-rce topic, visit your repo's landing page and select "manage topics."