Kaiyuan Zhang Kaiyuan Zhang | 张开元

Ph.D. Student
Department of Computer Science
Purdue University
305 N. University Street
West Lafayette, IN 47907
Email: zhan4057 at purdue dot edu
Google Scholar | dblp | Twitter | GitHub | LinkedIn

I am a Ph.D. student in the Department of Computer Science at Purdue University, co-advised by Prof. Ninghui Li and Prof. Xiangyu Zhang. My research interests focus on security and privacy in machine learning, especially in safe & responsible large language models, backdoor attacks and defenses, distributed training.

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. I was a research intern at NEC Labs America.

Research Opportunities: I am always happy to discuss and brainstorm; if you’re a researcher/student (especially underrepresented minorities) interested in security, privacy, or robust AI (Generative AI most recent, e.g., GPT, Llama, PaLM, DALL-E), please reach out with subject “[Prospective collaboration]” to zhan4057 at purdue dot edu.

What’s New

  • 03/2024. I will join Amazon Bedrock (Generative AI, Seattle) as an Applied Scientist Intern this summer!
  • 09/2023. Excited to be featured in NEC News for the summer intern project!
  • 05/2023. I will join NEC Labs America (San Jose) as a Research Intern this summer!
  • 11/2022. I am co-organizing the workshop on Backdoor Attacks and Defenses in Machine Learning (BANDS) at ICLR 2023! We invite submissions on any aspect of backdoor attacks and defenses in machine learning!
  • 10/2022. Excited to be featured in Purdue News for the Best Paper Award at ECCV 2022 AROW Workshop!

Publications [Google Scholar] [dblp] (*: equal contribution)

  • 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 (S&P 2024)
    [paper] [code] [slides] [poster] [website]
  • ODSCAN: Backdoor Scanning for Object Detection Models
    Siyuan Cheng*, Guangyu Shen*, Guanhong Tao, Kaiyuan Zhang, Zhuo Zhang, Shengwei An, Xiangzhe Xu, Yingqi Liu, Shiqing Ma, Xiangyu Zhang
    Proceedings of the 45th IEEE Symposium on Security and Privacy (S&P 2024)
    [paper] [code]
  • LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
    Siyuan Cheng, Guanhong Tao, Yingqi Liu, Guangyu Shen, Shengwei An, Shiwei Feng, Xiangzhe Xu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024)
    [paper] [code]
  • Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
    Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang, Qiuling Xu, Guanhong Tao, Guangyu Shen, Siyuan Cheng, Shiqing Ma, Pin-Yu Chen, Tsung-Yi Ho, Xiangyu Zhang
    Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)
    [paper] [code]
  • ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP
    Lu Yan, Zhuo Zhang, Guanhong Tao, Kaiyuan Zhang, Xuan Chen, Guangyu Shen, Xiangyu Zhang
    Proceedings of the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
    [paper]
  • Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
    Guangyu Shen*, Siyuan Cheng*, Guanhong Tao, Kaiyuan Zhang, Yingqi Liu, Shengwei An, Shiqing Ma, Xiangyu Zhang
    Proceedings of the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
    [paper] [code]
  • Your Exploit is Mine: Instantly Synthesizing Counterattack Smart Contract
    Zhuo Zhang, Zhiqiang Lin, Marcelo Morales, Xiangyu Zhang, Kaiyuan Zhang
    Proceedings of the 32nd USENIX Security Symposium (USENIX Security 2023)
    [paper]
  • ImU: Physical Impersonating Attack for Face Recognition System with Natural Style Changes
    Shengwei An, Yuan Yao, Qiuling Xu, Shiqing Ma, Guanhong Tao, Siyuan Cheng, Kaiyuan Zhang, Yingqi Liu, Guangyu Shen, Ian Kelk, Xiangyu Zhang
    Proceedings of the 44th IEEE Symposium on Security and Privacy (S&P 2023)
    [paper] [code]
  • Detecting Backdoors in Pre-trained Encoders
    Shiwei Feng, Guanhong Tao, Siyuan Cheng, Guangyu Shen, Xiangzhe Xu, Yingqi Liu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR 2023)
    [paper] [code]
  • 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)
    ECCV 2022 Workshop on Adversarial Robustness in the Real World (AROW 2022), Best Paper Award 🏆
    [paper] [code] [slides] [media coverage]
  • BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
    Siyuan Cheng, Guanhong Tao, Yingqi Liu, Shengwei An, Xiangzhe Xu, Shiwei Feng, Guangyu Shen, Kaiyuan Zhang, Qiuling Xu, Shiqing Ma, Xiangyu Zhang
    Proceedings of the 30th Network and Distributed System Security Symposium (NDSS 2023)
    [paper] [code]

Selected Awards

  • Best Paper Award at ECCV 2022 AROW Workshop, October 2022
  • Summer Research Grant, Purdue University, April 2022
  • China National Scholarship (0.2% in China), November 2016

Teaching

Guest Lecture

Teaching Assistant

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
  • Journal Reviewers
    • IEEE Transactions on Information Forensics and Security (TIFS)
    • IEEE Transactions on Dependable and Secure Computing (TDSC)
    • ACM Transactions on Privacy and Security (TOPS)
  • Conference/Workshop Reviewers
    • International Conference on Machine Learning (ICML), 2023, 2024
    • Neural Information Processing Systems (NeurIPS), 2023, 2024
    • International Conference on Learning Representations (ICLR), 2024
    • 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
  • External Reviewers
    • ACM Conference on Computer and Communications Security (CCS)
    • USENIX Security Symposium (USENIX Security)
    • IEEE/ACM International Conference on Automated Software Engineering (ASE)
    • ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA)
    • International Conference on Computer-Aided Verification (CAV)
  • Student Volunteers
    • ICML 2021, ICLR 2021, ECOOP/ISSTA 2021, CCS 2020, SIGMOD 2020

Personal

  • Kaiyuan Zhang’s name is pronounced as
  • Basketball is my favorite, I’ve been playing it weekly for more than ten years.
  • I love tennis, especially the moments of hitting the ball with the right amount of spin and force.
  • I also enjoy kayaking, quietly exploring a creek, enjoy views that can’t be seen from shore.
  • I consider myself lucky to be guided by helpful advice and instructions. Here are some notes I collect from time to time.