I am a Ph.D. student in the Department of Computer Sciences at the University of Wisconsin-Madison. I am advised by Prof. Patrick McDaniel and am a member of MadS&P research group. I have received my B.S. degree in Computer Science (Honors, advised by Adwait Nadkarni) and Mathematics from William & Mary.
My research mainly focuses on designing trustworthy Machine Learning models—evaluating and improving their robustness, explainability, and fairness. I am interested in the attack and defense mechanisms of adversarial machine learning from both architectural and training perspectives. Overall, I want to explore different angles of trustworthy AI and their broad applications in security and privacy.
In my free time, I love playing table tennis, biking, hiking, and snowboarding. Immersing myself in nature makes me feel incredibly refreshed and empowered!
On the Robustness Tradeoff in Fine-Tuning
Kunyang Li, Jean-Charles Noirot Ferrand, Ryan Sheatsley, Blaine Hoak, Yohan Beugin, Eric Pauley, Patrick McDaniel
Preprint, 2025
Alignment and Adversarial Robustness: Are More Human-Like Models More Secure?
Blaine Hoak*, Kunyang Li*, Patrick McDaniel
Preprint, 2025
On Adversarial and Common Robustness of Parameter-Efficient Fine-Tuning Strategies
Kunyang Li, Patrick McDaniel
Master Thesis, 2024
ParTEETor: A System for Partial Deployments of TEEs within Tor
Rachel King, Quinn Burke, Yohan Beugin, Blaine Hoak, Kunyang Li, Eric Pauley, Ryan Sheatsley, Patrick McDaniel
Workshop on Privacy in the Electronic Society (WPES), 2024
The Efficacy of Transformer-based Adversarial Attacks in Security Domains
Kunyang Li, Kyle Domico, Jean-Charles Noirot Ferrand, Patrick McDaniel
Proceedings of the IEEE Conference on Military Communications (MILCOM) - AI for Cyber Workshop, 2023
The Trade-off between Label Efficiency and Universality of Representations from Contrastive Learning
Zhenmei Shi*, Jiefeng Chen*, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha
International Conference on Learning Representations (ICLR), 2023 Spotlight (Acceptance Rate: 7.95%)
Static and Dynamic Analysis in Cryptographic-API Misuse Detection of Mobile Application
Kunyang Li
Undergraduate Honors Thesis, 2022
International Conference on Learning Representations (ICLR) Tiny Paper Track 2024, Tiny Paper Track 2023
USENIX Security Symposium (USENIX Security) 2025
IEEE Symposium on Security and Privacy (IEEE S&P) 2025
International Conference on Learning Representations (ICLR) 2025
ACM Conference on Computer and Communications Security (ACM CCS) 2024
USENIX Security Symposium (USENIX Security) 2023
Expand Your Horizons Madison - 2023, Volunteer