Saved in:
Bibliographic Details
Main Authors: Fang, Liancheng, Liu, Aiwei, Zou, Henry Peng, Chen, Yankai, Zhang, Hengrui, Deng, Zhongfen, Yu, Philip S.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.24267
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912403875168256
author Fang, Liancheng
Liu, Aiwei
Zou, Henry Peng
Chen, Yankai
Zhang, Hengrui
Deng, Zhongfen
Yu, Philip S.
author_facet Fang, Liancheng
Liu, Aiwei
Zou, Henry Peng
Chen, Yankai
Zhang, Hengrui
Deng, Zhongfen
Yu, Philip S.
contents We introduce MUSE, a watermarking algorithm for tabular generative models. Previous approaches typically leverage DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models exhibit significantly poorer invertibility compared to other modalities, compromising performance. Simultaneously, tabular diffusion models require substantially less computation than other modalities, enabling a multi-sample selection approach to tabular generative model watermarking. MUSE embeds watermarks by generating multiple candidate samples and selecting one based on a specialized scoring function, without relying on model invertibility. Our theoretical analysis establishes the relationship between watermark detectability, candidate count, and dataset size, allowing precise calibration of watermarking strength. Extensive experiments demonstrate that MUSE achieves state-of-the-art watermark detectability and robustness against various attacks while maintaining data quality, and remains compatible with any tabular generative model supporting repeated sampling, effectively addressing key challenges in tabular data watermarking. Specifically, it reduces the distortion rates on fidelity metrics by 81-89%, while achieving a 1.0 TPR@0.1%FPR detection rate. Implementation of MUSE can be found at https://github.com/fangliancheng/MUSE.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24267
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
Fang, Liancheng
Liu, Aiwei
Zou, Henry Peng
Chen, Yankai
Zhang, Hengrui
Deng, Zhongfen
Yu, Philip S.
Cryptography and Security
We introduce MUSE, a watermarking algorithm for tabular generative models. Previous approaches typically leverage DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models exhibit significantly poorer invertibility compared to other modalities, compromising performance. Simultaneously, tabular diffusion models require substantially less computation than other modalities, enabling a multi-sample selection approach to tabular generative model watermarking. MUSE embeds watermarks by generating multiple candidate samples and selecting one based on a specialized scoring function, without relying on model invertibility. Our theoretical analysis establishes the relationship between watermark detectability, candidate count, and dataset size, allowing precise calibration of watermarking strength. Extensive experiments demonstrate that MUSE achieves state-of-the-art watermark detectability and robustness against various attacks while maintaining data quality, and remains compatible with any tabular generative model supporting repeated sampling, effectively addressing key challenges in tabular data watermarking. Specifically, it reduces the distortion rates on fidelity metrics by 81-89%, while achieving a 1.0 TPR@0.1%FPR detection rate. Implementation of MUSE can be found at https://github.com/fangliancheng/MUSE.
title MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
topic Cryptography and Security
url https://arxiv.org/abs/2505.24267