# Observation-Level Watermarking and Detection for Tabular Data

arXiv: https://arxiv.org/abs/2607.10554 · HTML: https://mlsanity.com/paper/2607.10554/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 6 of 6)

- [Watermarking Text Generated by Black-Box Language Models](https://mlsanity.com/paper/2305.08883/) (2023)
- [Watermarking Generative Tabular Data](https://mlsanity.com/paper/2405.14018/) (2024)
- [PersonaMark: Personalized LLM watermarking for model protection and user attribution](https://mlsanity.com/paper/2409.09739/) (2024)
- [Adaptive and Robust Watermark for Generative Tabular Data](https://mlsanity.com/paper/2409.14700/) (2024)
- [MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection](https://mlsanity.com/paper/2505.24267/) (2025)
- [Robust Spectral Watermark for Synthetic Tabular Data](https://mlsanity.com/paper/2511.21600/) (2025)

## Abstract (arXiv)

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.