Publications
Preprint
- SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI
Kui Ren, Ziqi Yang, Li Lu, Jian Liu, Yiming Li, Jie Wan, Xiaodi Zhao, Xianheng Feng, Shuo Shao.
ArXiv Preprint. 2024.
[arXiv]
Accepted Papers
- Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
Shuo Shao*, Yiming Li*✉, Hongwei Yao, Yiling He, Zhan Qin✉, Kui Ren.
Network and Distributed System Security Symposium (NDSS). 2025.
[arXiv] [Code] [Sildes] [Poster] - FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model
Shuo Shao*, Wenyuan Yang*, Hanlin Gu, Zhan Qin✉, Lixin Fan, Qiang Yang, Kui Ren.
IEEE Transactions on Dependable and Secure Computing (TDSC). 2024.
[Paper] [arXiv] [Code] - PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
Cheng Wei, Yang Wang, Kuofeng Gao, Shuo Shao, Yiming Li, Zhibo Wang, Zhan Qin
To appear in IEEE Transactions on Information Forensics and Security (TIFS). 2024.
[arXiv] - Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring
Wenyuan Yang, Shuo Shao#, Yue Yang, Xiyao Liu✉, Ximeng Liu, Zhihua Xia, Gerald Schaefer, Hui Fang.
ACM Transactions on Intelligent Systems and Technology (TIST). 2023.
[Paper] [arXiv] [Code] - Secure Federated Learning Model Verification: A Client-side Backdoor Triggered Watermarking Scheme
Xiyao Liu, Shuo Shao#, Yue Yang, Kangming Wu, Wenyuan Yang✉, Hui Fang.
IEEE International Conference on Systems, Man, and Cybernetics (SMC). 2021.
[Paper]
*: Co-first authors; ✉: Corresponding author; #: First student author.
Patent
- 邵硕, 李一鸣, 秦湛, 任奎, 王宏韬, 马杏可, 冯振源. 一种基于非决策域方法的模型水印方法及装置. (发明专利, 已授权, CN202410553090.0, 授权日期: 2024/07/30)
- 乔一帆, 邵硕, 秦湛, 王志波, 任奎. 一种基于模型分割的大模型隐私保护推理方法. (发明专利, 已授权, CN202311418709.9, 授权日期: 2024/04/05)
- 邵硕, 李一鸣, 秦湛, 任奎, 王宏韬, 马杏可, 冯振源. 一种基于非决策域方法的模型指纹方法及装置. (发明专利, 已进入实质审查, CN202410664418.6)
- 李一鸣, 邵硕, 秦湛, 任奎, 王宏韬, 马杏可, 冯振源. 一种基于非决策域方法的数据集版权认证方法及装置. (发明专利, 已进入实质审查, CN202410664413.3)
- 邵硕, 秦湛. 一种神经网络模型的水印处理方法和装置. (发明专利, 已进入实质审查, CN202310117212.7)