# TabularMark: Watermarking Tabular Datasets for Machine Learning

arXiv: https://arxiv.org/abs/2406.14841 · HTML: https://mlsanity.com/paper/2406.14841/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 56 references that are in the map.
- First posted on arXiv 21 Jun 2024.

## Builds on (most cited first, 12 of 12)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Deep Learning for Financial Applications : A Survey](https://mlsanity.com/paper/2002.05786/) (2020)
- [HoloClean: Holistic Data Repairs with Probabilistic Inference](https://mlsanity.com/paper/1702.00820/) (2017)
- [Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks](https://mlsanity.com/paper/2302.01677/) (2023)
- [An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks](https://mlsanity.com/paper/2007.02460/) (2020)
- [A Comprehensive Survey of Watermarking Relational Databases Research](https://mlsanity.com/paper/1801.08271/) (2018)
- [A Somewhat Robust Image Watermark against Diffusion-based Editing Models](https://mlsanity.com/paper/2311.13713/) (2023)
- [Predicting Future Sales of Retail Products using Machine Learning](https://mlsanity.com/paper/2008.07779/) (2020)

## Built on by (most cited first, 8 of 8)

- [ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models](https://mlsanity.com/paper/2504.13061/) (2025)
- [Watermarking LLM Agent Trajectories](https://mlsanity.com/paper/2602.18700/) (2026)
- [Towards Robust Content Watermarking Against Removal and Forgery Attacks](https://mlsanity.com/paper/2604.06662/) (2026)
- [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)
- [Watermarking Generative Categorical Data](https://mlsanity.com/paper/2411.10898/) (2024)
- [Where is the Watermark? Interpretable Watermark Detection at the Block Level](https://mlsanity.com/paper/2512.14994/) (2025)
- [RaMark: Radioactive Watermarking for Generated Tabular Data](https://mlsanity.com/paper/2607.09000/) (2026)

## Abstract (arXiv)

Watermarking is broadly utilized to protect ownership of shared data while preserving data utility. However, existing watermarking methods for tabular datasets fall short on the desired properties (detectability, non-intrusiveness, and robustness) and only preserve data utility from the perspective of data statistics, ignoring the performance of downstream ML models trained on the datasets. Can we watermark tabular datasets without significantly compromising their utility for training ML models while preventing attackers from training usable ML models on attacked datasets? In this paper, we propose a hypothesis testing-based watermarking scheme, TabularMark. Data noise partitioning is utilized for data perturbation during embedding, which is adaptable for numerical and categorical attributes while preserving the data utility. For detection, a custom-threshold one proportion z-test is employed, which can reliably determine the presence of the watermark. Experiments on real-world and synthetic datasets demonstrate the superiority of TabularMark in detectability, non-intrusiveness, and robustness.