TAB-DRW: A DFT-based Robust Watermark for Generative Tabular Data

2025-11-26

AI Summary

Existing watermarking methods for provenance tracking of generative AI-synthesized tabular data suffer from high computational overhead, incompatibility with mixed discrete-continuous data, and weak resilience against post-generation edits. To address these challenges, this paper proposes an efficient and robust frequency-domain watermarking scheme. Our approach innovatively integrates discrete Fourier transform (DFT) with adaptive imaginary-part modulation and introduces a sorting-based pseudo-random bit generation mechanism, enabling zero-storage-overhead watermark embedding. Furthermore, we incorporate the Yeo-Johnson transformation and standardization to ensure compatibility with heterogeneous data types. Extensive evaluation across five benchmark datasets demonstrates that the embedded watermark achieves high detection accuracy, strong robustness against common post-processing attacks—including additive noise, row shuffling, and column pruning—and preserves high fidelity of the original tabular data.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Natural Language Processing: Generation
• Machine Learning: Privacy

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

The rise of generative AI has enabled the production of high-fidelity synthetic tabular data across fields such as healthcare, finance, and public policy, raising growing concerns about data provenance and misuse. Watermarking offers a promising solution to address these concerns by ensuring the traceability of synthetic data, but existing methods face many limitations: they are computationally expensive due to reliance on large diffusion models, struggle with mixed discrete-continuous data, or lack robustness to post-modifications. To address them, we propose TAB-DRW, an efficient and robust post-editing watermarking scheme for generative tabular data. TAB-DRW embeds watermark signals in the frequency domain: it normalizes heterogeneous features via the Yeo-Johnson transformation and standardization, applies the discrete Fourier transform (DFT), and adjusts the imaginary parts of adaptively selected entries according to precomputed pseudorandom bits. To further enhance robustness and efficiency, we introduce a novel rank-based pseudorandom bit generation method that enables row-wise retrieval without incurring storage overhead. Experiments on five benchmark tabular datasets show that TAB-DRW achieves strong detectability and robustness against common post-processing attacks, while preserving high data fidelity and fully supporting mixed-type features.

Problem

• Develops a watermarking method for synthetic tabular data
• Ensures traceability and robustness against post-processing attacks
• Handles mixed discrete-continuous data efficiently without large models

Innovation

• Uses DFT frequency domain watermark embedding
• Applies Yeo-Johnson transformation for feature normalization
• Introduces rank-based pseudorandom bit generation method