Xiaogeng Liu’s research is dedicated to advancing trustworthy AI by developing robust, scalable machine learning frameworks that stand up to real‐world adversarial challenges. His work focuses on designing innovative defense mechanisms that bolster a model’s resilience against unexpected perturbations and attacks, while preserving high performance under complex conditions. By leveraging adaptive strategies and rigorous robustness evaluations, he envisions these methods as foundational building blocks for a wide range of applications, including enhanced cybersecurity systems and reliable autonomous as well as decision-making systems in dynamic environments.
Xiaogeng Liu is a second-year PhD student at the University of Wisconsin-Madison, where he is advised by Chaowei Xiao. He received his Master's in Cybersecurity from Huazhong University of Science and Technology in 2023, where he had the privilege of working with Shengshan Hu in the TAI group. During his PhD he has focused on research in trustworthy AI and robust machine learning systems and has contributed to top international conferences. His work earned the Distinguished Paper Award at USENIX Security 2024.