CertDW: Towards Certified Dataset Ownership Verification via Conformal Prediction
Ting Qiao, Yiming Li, Jianbin Li, Yingjia Wang, Leyi Qi, Junfeng Guo, Ruili Feng, Dacheng Tao

TL;DR
This paper introduces CertDW, a certified dataset watermarking method that reliably verifies dataset ownership even under malicious attacks by using conformal prediction-based statistical measures.
Contribution
It presents the first certified dataset watermarking approach that ensures robust ownership verification against perturbations and attacks, based on statistical measures derived from conformal prediction.
Findings
CertDW effectively verifies dataset ownership under various perturbations.
The method demonstrates robustness against adaptive attacks in experiments.
It establishes a provable lower bound between statistical measures for verification.
Abstract
Deep neural networks (DNNs) rely heavily on high-quality open-source datasets (e.g., ImageNet) for their success, making dataset ownership verification (DOV) crucial for protecting public dataset copyrights. In this paper, we find existing DOV methods (implicitly) assume that the verification process is faithful, where the suspicious model will directly verify ownership by using the verification samples as input and returning their results. However, this assumption may not necessarily hold in practice and their performance may degrade sharply when subjected to intentional or unintentional perturbations. To address this limitation, we propose the first certified dataset watermark (i.e., CertDW) and CertDW-based certified dataset ownership verification method that ensures reliable verification even under malicious attacks, under certain conditions (e.g., constrained pixel-level…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPrivacy-Preserving Technologies in Data · Data Quality and Management · Cloud Data Security Solutions
