SPS Webinar: Towards Copyright-preserving Dataset Sharing via Dataset Ownership Verification
Date: 8 August 2024
Time: 7:30 AM ET (New York Time)
Presenter(s): Dr. Yiming Li, Dr. Junfeng Guo
Based on the IEEE Xplore® article:
"Black-Box Dataset Ownership Verification via Backdoor Watermarking", published in the IEEE Transactions on Information Forensics and Security, April 2023.
Original article: Download article
Original article will be made publicly available for download on the day of the webinar for 48 hours.
Abstract
High-quality open-sourced and commercial datasets significantly prompt AI prosperity. However, existing classical data protection methods (e.g., encryption) cannot protect their copyright by preventing unauthorized use for commercial purposes. In this webinar, the presenters will introduce the concept of dataset ownership verification (DOV), which is the first and only feasible solution to protect them. In general, DOV consists of two main stages, including dataset watermarking and ownership verification. In the first stage, dataset owners will introduce some imperceptible watermarked samples to generate the released watermarked version of the original dataset, so that all models trained on it will have specific distinctive prediction behaviors on particular samples while having normal behaviors on standard testing samples. In the second stage, given the API of a suspicious third-party deployed model, the dataset owners will detect whether it is trained on the protected dataset by examining its prediction behaviors on verification samples. They will first introduce the concept of DOV and the basic requirements of dataset watermarks used for DOV. After that, they will illustrate their method designs and their theoretical supports.
Biography
Yiming Li received the B.S. degree with honors in mathematics from Ningbo University in 2018 and the Ph.D. degree with honors in computer science and technology from Tsinghua University, in 2023.
He is currently a Research Fellow at Nanyang Technological University. Before that, he was a Research Professor in the State Key Laboratory of Blockchain and Data Security at Zhejiang University and also in HIC-ZJU. His research interests are in the domain of trustworthy ML and responsible AI, especially backdoor learning and AI copyright protection.
Dr. Li’s research has been published in multiple top-tier conferences and journals, such as ICLR, NeurIPS, and IEEE TIFS. He served as the Area Chair of ACM MM, the Senior Program Committee Member of AAAI, and the Reviewer of IEEE TPAMI, IEEE TIFS, IEEE TDSC, etc. His research has been featured by major media outlets, such as IEEE Spectrum. He was the recipient of the Best Paper Award at PAKDD in 2023 and the Rising Star Award at WAIC in 2023.
Junfeng Guo received the B.S. degree from the University of Electronic Science and Technology of China in 2018 and the Ph.D. degree in computer science from the University of Texas at Dallas in 2023.
He is currently a Research Associate in the Department of Computer Science from the University of Maryland. His research interests are in the domain of trustworthy ML and AI security, especially backdoor learning and copyright protection in deep learning.
Dr. Guo’s research has been published in multiple top-tier conferences and journals, such as ICLR, NeurIPS, and MobiCom. He served as the program committee member of ICLR, NeurIPS, ICML, etc., and the reviewer of IEEE TPAMI, IEEE TNNLS, etc.
