Pinned Loading

1. AI45Lab/OpenRT AI45Lab/OpenRT Public

   Open-source red teaming framework for MLLMs with 42+ attack methods

   Python 266 20

2. AI45Lab/OpenART AI45Lab/OpenART Public

   OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes agains…

   Python 101 9

3. EvoSynth EvoSynth Public

   EvoSynth is a SOTA automated LLM red-teaming framework that evolves executable, code-level jailbreak attack methods using multi-agent synthesis, evolutionary search, and self-correction.

   Python 60 9

4. 0606zt/PanoLlama 0606zt/PanoLlama Public

   [ICCV 2025 Highlight] Panorama Generation as a Next-Token Prediction Task.

   Python 48

5. LeakyCLIP LeakyCLIP Public

   LeakyCLIP is a CLIP inversion and privacy auditing framework for extracting training data signals from CLIP embeddings and analyzing membership leakage in multimodal models.

   Python 27 6

6. Chengsong-Huang/R-Zero Chengsong-Huang/R-Zero Public

   [ICLR2026] codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)

   Python 842 77