Kaiyuan Zhang Kaiyuan Zhang
How to pronounce?

PhD candidate
Purdue University
Office: 305 N. University Street
West Lafayette, IN, 47907-2107
Email: [email protected]
Google Scholar | dblp | Twitter | GitHub | LinkedIn

I am a PhD candidate of Computer Science at Purdue University, co-advised by Prof. Ninghui Li and Prof. Xiangyu Zhang. I am supported by the Amazon Fellowship and the Bilsland Dissertation Fellowship.

I am obsessed with simple solutions, passionate about deep understanding, and driven to build proactive systems. My research interests focus on security and privacy in machine learning. Currently, I study the security and privacy of large language models from an adversarial perspective, to understand and mitigate long-term threats and build proactive secure systems.

I will join Microsoft Research (NYC) as a Research Intern in Summer 2025. I was a research intern at Amazon AWS GenAI and NEC Labs America during my PhD. Before joining Purdue, I spent a wonderful year as a visiting graduate student at the University of Illinois at Urbana-Champaign, co-advised by Prof. Tao Xie and Prof. Tianyin Xu. I received an M.S. in Computer Science from the University of Texas at Dallas, advised by Prof. Wei Yang. I was a full-time research assistant advised by Prof. Wei Chen for 1.5 years at Zhejiang University before starting grad school.

Research Opportunities: I am always happy to discuss and brainstorm; if you’re a researcher/student interested in security, privacy, or GenAI (LLM agents most recent), please reach out to [email protected].

Office Hours: I owe a lot to my patient research mentors who generously spent their time helping me along the way. From September 2024, I will dedicate 2 hours each week to offer mentorship to undergrad and grad students on any topics you’d like to discuss. If you’re interested, please fill out the AMA form.

Selected Works [Full List] [Google Scholar] [dblp] (*: equal contribution)

  • LLM Agents Should Employ Security Principles
    Kaiyuan Zhang, Zian Su, Pin-Yu Chen, Elisa Bertino, Xiangyu Zhang, Ninghui Li
    Preprint 2025
    [paper]
  • SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
    Kaiyuan Zhang, Siyuan Cheng, Hanxi Guo, Yuetian Chen, Zian Su, Shengwei An, Yuntao Du, Charles Fleming, Ashish Kundu, Xiangyu Zhang, Ninghui Li
    Proceedings of the 34th USENIX Security Symposium (Security 2025)
    [paper (coming soon)] [code (coming soon)]
  • CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling
    Kaiyuan Zhang, Siyuan Cheng, Guangyu Shen, Bruno Ribeiro, Shengwei An, Pin-Yu Chen, Xiangyu Zhang, Ninghui Li
    Proceedings of the 32nd Network and Distributed System Security Symposium (NDSS 2025)
    [paper] [code] [slides] [twitter] [website]
  • Exploring the Orthogonality and Linearity of Backdoor Attacks
    Kaiyuan Zhang*, Siyuan Cheng*, Guangyu Shen, Guanhong Tao, Shengwei An, Anuran Makur, Shiqing Ma, Xiangyu Zhang
    Proceedings of the 45th IEEE Symposium on Security and Privacy (Oakland 2024)
    [paper] [code] [slides] [video] [poster] [twitter] [website]
  • FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
    Kaiyuan Zhang, Guanhong Tao, Qiuling Xu, Siyuan Cheng, Shengwei An, Yingqi Liu, Shiwei Feng, Guangyu Shen, Pin-Yu Chen, Shiqing Ma, Xiangyu Zhang
    Proceedings of the Eleventh International Conference on Learning Representations (ICLR 2023)
    Best Paper Award 🏆 in ECCV 2022 Workshop on Adversarial Robustness in the Real World (AROW 2022)
    [paper] [code] [slides] [media coverage]

Selected Honors & Awards

Teaching

Teaching Assistant

Guest Lectures

Professional Services

  • Organizers
    • The 1st Workshop on Backdoor Attacks and Defenses in Machine Learning (BANDS) at ICLR, 2023
    Machine Learning & Security Seminar at Purdue University, 2021, 2022, 2023
  • Program Committee Member
    • International Conference on Learning Representations (ICLR), 2024, 2025
    • International Conference on Machine Learning (ICML), 2023, 2024, 2025
    • Advances in Neural Information Processing Systems (NeurIPS), 2023, 2024, 2025
    • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    • IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
    • ICLR Workshop on Privacy Regulation and Protection in Machine Learning, 2024
    • ICML Workshop on Federated Learning and Analytics in Practice, 2023
    • ICML Workshop on Adversarial Machine Learning Frontiers, 2022
  • Journal Reviewers
    • IEEE Transactions on Information Forensics and Security (TIFS), 2023, 2024, 2025
    • IEEE Transactions on Dependable and Secure Computing (TDSC), 2023
    • ACM Transactions on Privacy and Security (TOPS), 2023
  • External Reviewers
    • ACM Conference on Computer and Communications Security (CCS), 2021, 2022, 2023, 2024, 2025
    • USENIX Security Symposium (Security), 2024, 2025
    • IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2025
    • ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA), 2024
    • IEEE/ACM International Conference on Automated Software Engineering (ASE), 2023
  • Student Volunteers
    • ICML 2021, ICLR 2021, ECOOP/ISSTA 2021, CCS 2020, SIGMOD 2020, etc.

Personal

  • Kaiyuan Zhang’s name is pronounced as
  • I love basketball and have been playing weekly for over ten years.
  • I’m a big fan of tennis, especially the moments of hitting the ball with the right amount of spin and force.
  • I enjoy kayaking, quietly exploring a creek, enjoy views that can’t be seen from shore.
  • I also like reading, drinking, cooking, traveling, and, of course, boba :-)
  • I consider myself lucky to be guided by helpful advice and instructions. Here are some notes I collect from time to time.