Team

Tianhao Li is a graduate student at Duke University and a visiting researcher at the SaFoLab, University of Wisconsin–Madison, working with Prof. Chaowei Xiao, Prof. Neil Gong, and Prof. Zhenyu Yang. His research focuses on evaluating and improving the safety and privacy of generative models and systems, especially in real-world domains such as healthcare, science, and the metaverse. He received a B.Eng. in Information Security in 2024 from North China University of Technology and worked as a Security Researcher (AI Red Teaming) at NSFOCUS and TOPSEC. He serves as journal referee for TIST, TAI, TBME, ESWA, EAAI, etc., and program committee for ARR, AAAI, IJCAI, ICLR, etc.. He also contributes to the MLCommons AI Risk & Reliability (AIRR) Working Group and to widely used open‑source project NVIDIA/garak. Know more at https://tianhao.li .

Chuangxin Chu is a researcher and graduate student in Electrical and Electronic Engineering at Nanyang Technological University, Singapore. He holds a Bachelor's degree with honours in Software Engineering from University College Dublin, Ireland. He has worked at the AI Agent Research Institute of Continental (Fortune Global 500) and as a post-training reinforcement learning researcher at Baidu, where he focused on replicating and extending cross-domain generalization GRPO algorithms. His research centers on AI security and large model security, aiming to enhance the robustness and trustworthiness of advanced AI systems.

Yujia Zheng is a graduate student at Duke University specializing in Trustworthy Artificial Intelligence. She holds a Bachelor of Engineering in Information Security. Her research focuses on adversarial robustness, with project experience spanning natural language processing, VR/AR/XR, and biomedical AI. She previously served as a research intern at the Science and Technology on Integrated Information System Laboratory, Institute of Software, Chinese Academy of Sciences, contributing to publications at venues including ICLR, EMNLP, AAAI, AAPM, and ASTRO. Yujia is also a reviewer for AAAI, CHI, and COLING. She has received multiple national-level awards in security, mathematical modeling, and digital media.