Year: 2026
Type: article
Abstract: In this paper, we introduce a simple yet effective continuous tabular data watermarking mechanism with statistical guarantees. We show theoretically that the proposed watermark can be effectively detected, while faithfully preserving the data fidelity. The general idea of the watermarking mechanism is to achieve the watermarking through a strategic embedding based on simple data binning. Specifically, it divides the feature’s value range into finely segmented intervals and embeds watermarks into selected “green list" intervals. To detect the watermarks, we develop a principled statistical hypothesis-testing framework with minimal assumptions: it remains valid as long as the underlying data distribution has a continuous density function. Furthermore, we demonstrate robustness of the proposed watermarking mechanism against various attacks. The watermarking efficacy is demonstrated through rigorous theoretical analysis and empirical validation, highlighting its utility in enhancing the security of synthetic and real-world datasets with continuous tabular features.
Authors: Hengzhi He, Peiyu Yu, Junpeng Ren, Ying Nian Wu, Guang Cheng
Institution: University of California, Los Angeles
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4398796381
