ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark

High-quality public datasets significantly prompt the prosperity of deep neural networks (DNNs). Currently, dataset ownership verification (DOV), which consists of dataset watermarking and ownership verification, is the only feasible so-lution to protect their copyright by preventing unauthorized use. In this paper, we revisit existing DOV methods and find that they all mainly focused on the first stage by designing different types of dataset watermarks and directly exploiting watermarked samples as the verification samples for ownership verification. As such, their success relies on an underlying assumption that verification is a one-time and privacy-preserving process, which does not necessarily hold in practice. To alleviate this problem, we propose ZeroMark to conduct ownership verification without disclosing dataset-specified watermarks. Our method is inspired by our empirical and theoretical findings of the intrinsic property of DNNs trained on the watermarked dataset. Specifically, ZeroMark first generates the closest boundary version of given benign samples and calculates their boundary gradients under the label-only black-box setting. After that, it examines whether the given suspicious method has been trained on the protected dataset by performing a hypothesis test, based on the cosine similarity measured on the boundary gradients and the watermark pattern. Extensive experiments on benchmark datasets verify the effectiveness of our ZeroMark and its resistance to potential adaptive attacks. The codes for reproducing our main experiments are publicly available at GitHub.