Xiaogeng Liu - Team leader
Xiaogeng Liu is a second-year Ph.D. student in Information Science at the University of Wisconsin-Madison. His research primarily focuses on the safety and security challenges associated with large language models, with an emphasis on understanding and mitigating vulnerabilities such as jailbreak and prompt injection attacks.
Peiran Li
Peiran Li is a third-year undergraduate student in Computer Science at the University of Wisconsin-Madison. His research focuses on the cutting-edge domains of trustworthy large language models, and large language model operating systems.
Jiongxiao Wang
Jiongxiao Wang is a second-year Ph.D. student in Information Science at the University of Wisconsin-Madison. His research primarily focuses on the safety and security challenges associated with LLMs. He is particularly focused on data poisoning attacks during the LLMs' training process.
Yingzi Ma
Yingzi Ma is a first-year Ph.D. student in Information Science at the University of Wisconsin-Madison. His research vision is centered on building foundational language models that deeply comprehend multimodal information—encompassing text, images, videos, and beyond—and align effectively with human intents expressed through various modalities.
Jingyu Huang
Jingyu Huang is a third-year undergraduate student in Computer Science at the University of Wisconsin-Madison. His research focuses on leveraging LLMs’ logical reasoning capabilities to design comprehensive attack systems. He aims to build comprehensive frameworks that can autonomously plan and execute adaptive attack strategies, leveraging LLMs’ reasoning capabilities to identify vulnerabilities and optimize attack success rates through dynamic and systematic interactions.
Hao Wu
Hao Wu is a first-year CS PhD student at the University of Wisconsin-Madison. His research focuses on accessing and mitigating harmful effects of LLM in different systems. He aims to reduce tech abuse, especially LLM abuse these days, through technical and social interventions.
Chaowei Xia - Faculty advisor
Chaowei Xiao is an assistant professor at the University of Wisconsin-Madison, with a keen interest in exploring the safety and security of large language model systems and studying their roles across various application domains. He obtained his Ph.D. from the University of Michigan, Ann Arbor.
