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

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.

Key Contributions

• Post-editing frequency-domain watermarking scheme (TAB-DRW) that normalizes heterogeneous tabular features via Yeo-Johnson transformation and embeds pseudorandom bits in DFT imaginary components
• Novel rank-based pseudorandom bit generation enabling row-wise watermark retrieval without storage overhead
• Demonstrated robustness against common post-processing attacks (deletion, value modification) across five benchmark datasets while supporting mixed continuous/discrete tabular data

🛡️ Threat Analysis

Details

Similar Papers