Pinned Loading

1. AI-secure/RedCode AI-secure/RedCode Public

   [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents

   Python 71 10

2. AI-secure/MMDT AI-secure/MMDT Public

   Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models

   Jupyter Notebook 28 2

3. AI-secure/PolyGuard AI-secure/PolyGuard Public

   Python 19 2

4. RedCodeAgent RedCodeAgent Public

   [ICLR 2026] Official implementation for "RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents"

   3