Zeyu Zhao

Zeyu Zhao

About Me

Zeyu Zhao

I am a Ph.D. student in the School of Computer Science, Shanghai Jiao Tong University.

My research lies at the intersection of Artificial Intelligence, AI Security, and Adversarial Machine Learning, with a particular focus on:

  • Video Adversarial Examples
  • Reversible Adversarial Examples
  • Privacy Protection
  • Trustworthy and Secure AI Systems

I am currently working on research problems related to AI security evaluation, LLM robustness, and adversarial security of diffusion models.

Education

  • Ph.D. in Cyberspace Security, Shanghai Jiao Tong University, 2022–Present
    Advisor: Prof. Xinghao Jiang

  • M.S. in Cyberspace Security, Shanghai Jiao Tong University, 2020–2022

  • B.S. in Information Security, Shanghai Jiao Tong University, 2016–2020

Selected Publications

  1. Zeyu Zhao, Ke Xu, Tanfeng Sun, Xinghao Jiang.
    SRAP: Robust and Transferable Self-Reversible Adversarial Patch for Image Privacy Protection.
    IEEE Transactions on Information Forensics and Security (TIFS), vol. 21, pp. 3689–3702, 2026.

  2. Zeyu Zhao, Ke Xu, Tanfeng Sun, Xinghao Jiang.
    ASGA: Attention-based Sparse Global Attack to Video Action Recognition.
    IEEE Transactions on Dependable and Secure Computing (TDSC), 2025.

  3. Zeyu Zhao, Ke Xu, Laijin Meng, Tanfeng Sun, Xinghao Jiang.
    INN-RAE: Reversible Adversarial Examples Based on Invertible Neural Networks for Facial Protection.
    Expert Systems with Applications (ESWA), 2025.

  4. Zeyu Zhao, Yueneng Wang, Ke Xu, Tanfeng Sun, Xinghao Jiang.
    HEVC Video Adversarial Samples Detection via Joint Features of Compression and Pixel Domains.
    IEEE Transactions on Information Forensics and Security (TIFS), vol. 20, pp. 488–503, 2024.

  5. Zeyu Zhao, Ke Xu, Xinghao Jiang, Tanfeng Sun.
    Research on Video Adversarial Attack with Long Living Cycle.
    Uncertainty in Artificial Intelligence (UAI), pp. 2374–2382, 2022.

  6. Shijie Hou, Xinighao Jiang, Qiang Xu, Ke Xu, Zeyu Zhao, Yinuo Ge. Deepfake Detection via Data-Level Multi Stream Assessment. IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2026.

  7. Mengdi Dong, Ke Xu, Xinghao Jiang, Zeyu Zhao, Tanfeng Sun.
    Feature-Aware Transferable Adversarial Attacks on Visual Object Tracking.
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 35, no. 7, pp. 7075–7089, 2025.

  8. Haotian Ma, Ke Xu, Xinghao Jiang, Zeyu Zhao, Tanfeng Sun.
    Transferable Black-Box Attack Against Face Recognition with Spatial Mutable Adversarial Patch.
    IEEE Transactions on Information Forensics and Security (TIFS), vol. 18, pp. 5636–5650, 2023.

  9. Laijin Meng, Xinghao Jiang, Tanfeng Sun, Zeyu Zhao, Qiang Xu.
    A Robust Coverless Video Steganography Based on the Similarity of Inter-Frames.
    IEEE Transactions on Multimedia (TMM), vol. 26, pp. 5996–6011, 2023.

  10. 蒋兴浩, 赵泽宇, 许可.
    基于视觉的飞行器智能目标检测对抗攻击技术.
    空天防御, vol. 4, no. 1, pp. 8–13, 2021.

  11. Hanqi Zhang, Ke Xu, Xinghao Jiang, Tanfeng Sun, Zeyu Zhao.
    When does Adversarial Training Hurt Adversarial Robustness in Phase Translation of Training Data?
    2026 International Conference on Intelligent Computing (ICIC 2026), Oral Presentation, to appear in Lecture Notes in Computer Science (LNCS), Springer Nature, 2026.

Contact