Zhuang Peiyu

Zhuang Peiyu

Postdoctoral Fellow in multimedia content security, AI safety, and 3D reconstruction

Peiyu Zhuang

I am a Postdoctoral Fellow at the School of Cyber Science and Technology, Sun Yat-sen University, advised by Prof. Xiaochun Cao. I received my Ph.D. from the College of Electronics and Information Engineering at Shenzhen University in 2023, under the joint supervision of Prof. Jiwu Huang and Assistant Prof. Haodong Li. Before joining Sun Yat-sen University in January 2026, I worked as a Senior Algorithm Engineer at Huawei's 2012 Laboratories from July 2023 to January 2026. My research focuses on multimedia content security, artificial intelligence safety, image tampering localization, and 3D reconstruction. My work has appeared in venues and journals including IEEE TIFS, AAAI, ESWA, and ICRA.

Publications Google Scholar SYSU Profile Email
282
Citations
5
h-index
3
i10-index
12
Articles

Google Scholar metrics last synced on June 29, 2026.

Research Focus

Image Tampering Localization

Robust methods for detecting and localizing manipulated image regions under challenging real-world conditions.

Multimedia Content Security

Forensic analysis and protection of visual media, with attention to authenticity, reliability, and generalization.

AI Safety

Understanding and mitigating security risks in AI-generated and identity-preserving visual content.

3D Reconstruction

Exploring dynamic scene reconstruction and visual synthesis for reliable 3D perception and generation.

Selected Publications

  1. Image tampering localization using a dense fully convolutional network P. Zhuang, H. Li, S. Tan, B. Li, J. Huang. IEEE TIFS, 2021. CAS Q1 Top Journal, CCF-A.
  2. ReLoc: A restoration-assisted framework for robust image tampering localization P. Zhuang, H. Li, R. Yang, J. Huang. IEEE TIFS, 2023. CAS Q1 Top Journal, CCF-A.
  3. Towards generalizable and robust image tampering localization with multi-task learning and contrastive learning H. Li, P. Zhuang, Y. Su, J. Huang. Expert Systems with Applications, 2025. CAS Q1 Top Journal; corresponding author.
  4. Unveiling the attribute misbinding threat in identity-preserving models J. Fu, J. Zeng, Y. Jiang, P. Zhuang, B. Chen, S. Lu, J. Yang. AAAI, 2026. Oral presentation, CCF-A.

View all publications

Patents

  1. Peiyu Zhuang, Haodong Li, Jiwu Huang. Method for generating an image tampering localization model, image tampering localization method, and device. China, CN202010651539.9, authorized July 25, 2023.
  2. Peiyu Zhuang, Yanjie Hu, Haodong Li, Jiwu Huang. Method and system for generating Photoshop-tampered images. China, CN202010676938.0, authorized March 22, 2024.

Awards

  1. First Prize, Outstanding Paper Award of the Guangdong Computer Society, 2025. First awardee.
  2. First Prize, Outstanding Paper Award of the Guangdong Computer Society, 2023. First awardee.
  3. Champion, DeeperForensics Challenge 2020. Second awardee.