Portrait of Kai Yao

Kai Yao

PhD Candidate, School of Informatics, University of Edinburgh

[email protected] · Google Scholar · CV (PDF) · LinkedIn

I study secure and trustworthy machine learning, with research interests including the security, privacy, and fairness of AI models. My current research projects focus on model provenance for generative image models, where I develop novel techniques and conduct robustness evaluations of model fingerprinting and model watermarking (PhD advisor: Dr. Marc Juarez).

  • AI Security
  • Generative AI
  • Computer Vision

Education

University of Edinburgh
Ph.D. in Informatics (expected graduation: Nov. 2026).
Johns Hopkins University
M.Sc. in Mechanical Engineering; research focus on AI for bioscience.
Fudan University
B.Sc. in Theoretical Mechanics.

News

Publications

  1. Yao K, Juarez M.
    arXiv preprint, 2025. To appear in 2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML).
  2. Yao K, Juarez M.
    arXiv preprint, 2025.
  3. Yao K, Juarez M.
    2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML).
  4. Rochman ND*, Yao K*, Perez-Gonzalez NA*, Wirtz D, Sun SX.
    Bio-protocol, 2020.
  5. Yao K*, Rochman ND*, Sun SX.
    Journal of Cell Science, 2020.
  6. Perez-Gonzalez NA*, Rochman ND*, Yao K* et al.
    Journal of Cell Biology, 2019.
  7. Yao K*, Rochman ND*, Sun SX.
    Scientific Reports, Nature Publishing Group, 2019.
  8. Zhang Q, Meng Z, Zhang Y, Yao K et al.
    BioMedical Engineering OnLine, 2016.

Note: * denotes equal contribution (co-first author).

Teaching and Tutoring