dsp-dr/defcon33-model-security-lab

Security research on AI/ML model vulnerabilities based on DEF CON 33 presentations. Demonstrates pickle RCE, TorchScript exploitation, ONNX injection, model poisoning, and integrated LLM attacks with PromptMap2.

语言：Python · GitHub 星标：9 · Fork：1

话题：ai-security · defcon · llm-security · machine-learning · model-security · pickle · prompt-injection · pytorch

在 GitHub 上查看原仓库