English

A self-attention-based differentially private tabular GAN with high data utility

Machine Learning 2023-12-21 v1 Cryptography and Security Databases

Abstract

Generative Adversarial Networks (GANs) have become a ubiquitous technology for data generation, with their prowess in image generation being well-established. However, their application in generating tabular data has been less than ideal. Furthermore, attempting to incorporate differential privacy technology into these frameworks has often resulted in a degradation of data utility. To tackle these challenges, this paper introduces DP-SACTGAN, a novel Conditional Generative Adversarial Network (CGAN) framework for differentially private tabular data generation, aiming to surmount these obstacles. Experimental findings demonstrate that DP-SACTGAN not only accurately models the distribution of the original data but also effectively satisfies the requirements of differential privacy.

Keywords

Cite

@article{arxiv.2312.13031,
  title  = {A self-attention-based differentially private tabular GAN with high data utility},
  author = {Zijian Li and Zhihui Wang},
  journal= {arXiv preprint arXiv:2312.13031},
  year   = {2023}
}
R2 v1 2026-06-28T13:57:33.647Z