# DTGAN: Differential Private Training for Tabular GANs

arXiv: https://arxiv.org/abs/2107.02521 · HTML: https://mlsanity.com/paper/2107.02521/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 14 of 14)

- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Subsampled R'enyi Differential Privacy and Analytical Moments Accountant](https://mlsanity.com/paper/1808.00087/) (2018)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [On Wasserstein Two Sample Testing and Related Families of Nonparametric Tests](https://mlsanity.com/paper/1509.02237/) (2015)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [DP-CGAN: Differentially Private Synthetic Data and Label Generation](https://mlsanity.com/paper/2001.09700/) (2020)
- [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators](https://mlsanity.com/paper/2006.08265/) (2020)
- [Differentially Private Synthetic Medical Data Generation using Convolutional GANs](https://mlsanity.com/paper/2012.11774/) (2020)

## Built on by (most cited first, 7 of 7)

- [Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe](https://mlsanity.com/paper/2210.14348/) (2022)
- [Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilities](https://mlsanity.com/paper/2405.20959/) (2024)
- [Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis](https://mlsanity.com/paper/2307.15424/) (2023)
- [ComicGAN: Text-to-Comic Generative Adversarial Network](https://mlsanity.com/paper/2109.09120/) (2021)
- [Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review](https://mlsanity.com/paper/2306.00687/) (2023)
- [Effective and Privacy preserving Tabular Data Synthesizing](https://mlsanity.com/paper/2108.10064/) (2021)
- [Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation](https://mlsanity.com/paper/2512.00638/) (2025)

## Abstract (arXiv)

Tabular generative adversarial networks (TGAN) have recently emerged to cater to the need of synthesizing tabular data -- the most widely used data format. While synthetic tabular data offers the advantage of complying with privacy regulations, there still exists a risk of privacy leakage via inference attacks due to interpolating the properties of real data during training. Differential private (DP) training algorithms provide theoretical guarantees for training machine learning models by injecting statistical noise to prevent privacy leaks. However, the challenges of applying DP on TGAN are to determine the most optimal framework (i.e., PATE/DP-SGD) and neural network (i.e., Generator/Discriminator)to inject noise such that the data utility is well maintained under a given privacy guarantee. In this paper, we propose DTGAN, a novel conditional Wasserstein tabular GAN that comes in two variants DTGAN_G and DTGAN_D, for providing a detailed comparison of tabular GANs trained using DP-SGD for the generator vs discriminator, respectively. We elicit the privacy analysis associated with training the generator with complex loss functions (i.e., classification and information losses) needed for high quality tabular data synthesis. Additionally, we rigorously evaluate the theoretical privacy guarantees offered by DP empirically against membership and attribute inference attacks. Our results on 3 datasets show that the DP-SGD framework is superior to PATE and that a DP discriminator is more optimal for training convergence. Thus, we find (i) DTGAN_D is capable of maintaining the highest data utility across 4 ML models by up to 18% in terms of the average precision score for a strict privacy budget, epsilon = 1, as compared to the prior studies and (ii) DP effectively prevents privacy loss against inference attacks by restricting the success probability of membership attacks to be close to 50%.