Observation-Level Watermarking and Detection for Tabular Data
2026-07-12 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new method called STAMP to add watermarks to tabular data, which includes numbers and categories, to prove the data's authenticity. This method works well even when only one piece of data is checked, making it easier to detect if data has been altered or copied. Their approach preserves the original data's quality and works reliably in tests on both simulated and real datasets. They also provide mathematical proof that their detection method improves with more data.
generative AIwatermarkingtabular datacategorical datanumerical datadata fidelityasymptotic consistencydetection accuracysimulation studiesdata authenticity
Authors
Dongyu Cui, Xuan Bi
Abstract
With the development of generative AI, watermarking techniques have been widely used to detect the authenticity of AI-generated data and protect the rights of users and creators. While it is already well applied in data types including imaging and text data, watermarking tabular data is still under-explored. Existing methods primarily focus on numerical data, leaving discrete, categorical, and mixed data less studied. In this work, we propose STAMP (Single-observation Tabular Attribution and Marking Procedure), a novel framework for watermarking tabular data that can accommodate and preserve a wide range of distributions. We also develop a corresponding detection mechanism, which can reliably identify watermarks even when the sample size is as small as one. We establish theoretical guarantees for asymptotic consistency and detection accuracy. Finally, through extensive simulation studies and two real-data applications, we demonstrate that the proposed method is effective and robust to subsetting, while maintaining data fidelity and a high detection rate.