Chaowei Xiao 2024 Early Career Fellow
Affiliation Assistant Professor, University of Wisconsin, Madison Hard Problem Solved AI’s continually evolving safety and security, robustness, performance, output challenges and other shortcomings that may cause harm or erode public trust of AI systems, especially in safety-critical applications and uses where societal stakes and potential for societal harm are high.

Chaowei Xiao is an Assistant Professor at University of Wisconsin, Madison. His research focuses on the intersection of machine learning and security, with the goal to build secure and safe machine learning systems. He has received the ACM Gordon Bell Special Prize and multiple best paper awards at USENIX Security, MobiCOM and ESWN. His research work featured in multiple media outlets, including Nature, Wired, Fortune, and The New York Times. One of Dr. Xiao’s research output is also on display at the London Science Museum. For more information, visit his website: https://xiaocw11.github.io/

AI2050 Project

Modern AI systems possess remarkable capabilities, yet they continue to exhibit safety and security vulnerabilities. Chaowei’s AI2050 project, aims to advance our understanding of safety and security challenges in modern AI models and systems. This project focuses on developing cutting-edge red-teaming tools to automatically discover and assess vulnerabilities in AI systems, as well as evaluating the harmful consequences introduced by modern AI technologies. Additionally, Chaowei will explore principled methods to enhance the security of AI systems, ensuring they become safer, more robust, and aligned with societal values.