TableMark: A Multi-bit Watermark for Synthetic Tabular Data

TL;DR

TableMark introduces a robust multi-bit watermarking scheme for synthetic tabular data that ensures high traceability, resilience to attacks, and maintains data utility, outperforming existing methods.

Contribution

The paper presents a novel multi-bit watermarking scheme, TableMark, with an optimization-based encoding process for synthetic tabular data, enhancing robustness and utility.

Findings

Effective traceability of multiple users

High resilience to watermark removal attacks

Preserves data utility better than existing schemes

Abstract

Watermarking has emerged as an effective solution for copyright protection of synthetic data. However, applying watermarking techniques to synthetic tabular data presents challenges, as tabular data can easily lose their watermarks through shuffling or deletion operations. The major challenge is to provide traceability for tracking multiple users of the watermarked tabular data while maintaining high data utility and robustness (resistance to attacks). To address this, we design a multi-bit watermarking scheme TableMark that encodes watermarks into synthetic tabular data, ensuring superior traceability and robustness while maintaining high utility. We formulate the watermark encoding process as a constrained optimization problem, allowing the data owner to effectively trade off robustness and utility. Additionally, we propose effective optimization mechanisms to solve this problem to enhance the data utility. Experimental results on four widely used real-world datasets show that TableMark effectively traces a large number of users, is resilient to attacks, and preserves high utility. Moreover, TableMark significantly outperforms state-of-the-art tabular watermarking schemes.