π§ About Me
Hi there! I am a PhD student majoring in Cyberspace Security at Nanjing University of Aeronautics and Astronautics, under the supervision of Prof. Yushu Zhang.
Research Interests:
π€ For my PhD study, my primary focus is on human-centered visual privacy protection. Specifically, I aim to design practical tools that address privacy concerns in real-world applications, such as social scenarios, where users often face significant privacy risks. By combining theoretical research with practical implementation, I hope to develop solutions that are not only effective but also user-friendly and widely adoptable.
π₯ News
- 2025.04.05: π Our paper on tailor-made protection is accepted by TDSC
- 2025.04.04: π My Master's degree thesis got the excellent thesis award (NUAA)
π Selected Publications
( * indicates the corresponding author. Full list of publications)
Accepted
Tailor-made Face Privacy Protection via Class-wise Targeted Universal Adversarial Perturbations
[2025 TDSC], CCF A
Yushu Zhang, Zixuan Yang, Tao Wang*, Zhongyun Hua, and Jian Weng
- This paper proposes a user-specific universal mask for face privacy, which can map all face images of the same user to a pre-defined virtual identity.
Seeing is not Believing: An Identity Hider for Human Vision Privacy Protection
[2025 TBIOM], [code]
Tao Wang, Yushu Zhang*, Zixuan Yang, Xiangli Xiao, Hua Zhang, Zhongyun Hua.
- This paper proposes an identity hider, which can prevents humans from observing the identity but allows machines to extract the identity.
Beyond Privacy: Generating Privacy-Preserving Faces Supporting Robust Image Authentication
[2025 TIFS], CCF A, [code] [TL;DR]
Tao Wang, Wenying Weng*, Xiangli Xiao, Zhongyun Hua, Yushu Zhang, Yuming Fang
- This paper proposes AIDPro, which can embed messages in a robust way for image authentication while altering identity for privacy protection.
Make Privacy Renewable! Generating Privacy-Preserving Faces Supporting Cancelable Biometric Recognition
[2024 ACM MM], CCF A, [code]
Tao Wang, Yushu Zhang*, Xiangli Xiao, Lin Yuan, Zhihua Xia, Jian Weng
- This paper proposes CanFG, which can embed virtual identity for supporting cancelable biometrics while removing physical identity for privacy protection.
Security and Privacy on Generative Data in AIGC: A Survey
[2024 CSUR], IF: 23.8, [reading list]
Tao Wang, Yushu Zhang*, Shuren Qi, Ruoyu Zhao, Zhihua Xia, and Jian Weng
- This survey reviews the security and privacy on generative data in AIGC, particularly for the first time analyzing them from the perspective of information security properties, including privacy, controllability, authenticity, and compliance.
π Honors and Awards
- ACM MM Honorable Mention Award, 2024
- National Scholarships for Postgraduate Students, 2023
- Second Prize of the Fifth National Crypto-math Challenge at the National Level, 2020
π Projects
- Postgraduate Research & Practice Innovation Program of Jiangsu Province, Friendly Face Privacy Protection Based on AIGC, 2025-2026, PI
- Postgraduate Research & Practice Innovation Program of NUAA with Excellent Finishes, Face Privacy Protection with Preserved Identification Utility, 2022-2023, PI
- Undergraduate Training Programs for Innovation and Entrepreneurship of Anhui Province with Excellent Finishes, Personalized Learning Resource Recommendation Based on User Modeling, 2019-2021, PI
π Educations
- π 2024.04 - Now,Β Β Β Ph.D., Nanjing University of Aeronautics and Astronautics, Cyberspace Security, China, supervised by Prof. Yushu Zhang.
- π 2021.09 - 2024.04, M.S., Nanjing University of Aeronautics and Astronautics, Cyberspace Security, China, supervised by Prof. Yushu Zhang.
- π 2017.09 - 2021.06, B.E., Anhui Normal University, Computer Science and Technology, China, supervised by Prof. Liping Sun.
π¬ Services
- Journal Reviewer: TKDEοΌTDSC
- Conference Reviewer: MM, ICLR, KDD