Watermarking Continuous Tabular Data Generation

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

Institutions

Publication Details

Journal
Journal of the American Statistical Association
Published
2026-11-19
DOI
https://doi.org/10.1080/01621459.2026.2750529
Citations
18
Primary Topic
Advanced Steganography and Watermarking Techniques
Type
article
Field-Weighted Citation Impact
12.05
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Watermarking Continuous Tabular Data Generation

Hengzhi He, Ying Nian Wu, Junpeng Ren, Peiyu Yu
18 citations
Journal of the American Statistical Association
Advanced Steganography and Watermarking Techniques
12.05
article

Watermarking Continuous Tabular Data Generation

Hengzhi He, Ying Nian Wu, Junpeng Ren, Peiyu Yu
article en
18 citations

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.

Journal of the American Statistical Association
University of California, Los Angeles (US)
Openalex Percentile: Top 1%
Advanced Steganography and Watermarking Techniques
12.05
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon