---
title: README
emoji: 🚀
colorFrom: red
colorTo: blue
sdk: gradio
pinned: false
---

* Welcome to TrustSafeAI! We are a reseach group focusing on evaluating and improving AI safety. 
* If you are interested in joining us, please reach out to [Pin-Yu Chen](pinyuchen.tw@gmail.com)
* Team Members and Projects:

|   Member      | Project                                                                                                                                                              | Webpage                                                      |
| ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------ |
| Xiaomeng Hu | [RADAR](https://huggingface.co/spaces/TrustSafeAI/RADAR-AI-Text-Detector) (NeurIPS'23), [Gradient Cuff](https://huggingface.co/spaces/TrustSafeAI/GradientCuff-Jailbreak-Defense) (NeurIPS'24) | [webpage](https://gregxmhu.github.io/)|
| Lei Hsiung  | [NeuralFuse](https://huggingface.co/spaces/TrustSafeAI/NeuralFuse) (NeurIPS'24), [NCTV](https://huggingface.co/spaces/TrustSafeAI/NCTV) (TMLR; AAAI'23), [CARBEN](https://hsiung.cc/CARBEN/) (CVPR'23; IJCAI'22)| [webpage](https://hsiung.cc/)|
| Zhi-Yi Chin | [P4D](https://huggingface.co/collections/TrustSafeAI/p4d-red-teamer-665d652c2b4ea4231cfda5c4) (ICML'24) | [webpage](https://joycenerd.github.io/)|
| Barry Xiong | [DPP](https://huggingface.co/spaces/TrustSafeAI/Defensive-Prompt-Patch-Jailbreak-Defense)| - |
| Zaitang Li  | [GREAT Score](https://huggingface.co/spaces/TrustSafeAI/GREAT-Score) (NeurIPS'24)|-|
| Yung-Chen Tang|[NCTV](https://huggingface.co/spaces/TrustSafeAI/NCTV) (TMLR; AAAI'23)   , [LLM-Physical-Safety](https://huggingface.co/spaces/TrustSafeAI/LLM-physical-safety)|[webpage](https://sites.google.com/view/yungchentang)|
| Zhiyuan He  |[BEYOND](https://huggingface.co/spaces/allenhzy/Be-Your-Own-Neighborhood) (ICML'24)| - |
| Yujun Zhou  |[LLM LabSafety](https://huggingface.co/datasets/yujunzhou/LabSafety_Bench)| - |
| Xiangyu Qi  | [LLM Finetuning Safety](https://huggingface.co/datasets/LLM-Tuning-Safety/HEx-PHI) (ICLR'24)| [webpage](https://xiangyuqi.com/)|
| Kuo-Han (Johnson) Hung| [Attention Tracker](https://huggingface.co/spaces/TrustSafeAI/Attention-Tracker) (NAACL'25) | [webpage](https://khhung-906.github.io/)|
| Pin-Yu Chen | All (research supervisor) |  [webpage](https://sites.google.com/site/pinyuchenpage/home) |