DTGAN: Differential Private Training for Tabular GANs

07/06/2021
by   Aditya Kunar, et al.
0

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 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

READ FULL TEXT

page 1

page 2

page 3

page 4

04/01/2022

CTAB-GAN+: Enhancing Tabular Data Synthesis

While data sharing is crucial for knowledge development, privacy concern...
08/20/2020

Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning

Data holders are increasingly seeking to protect their user's privacy, w...
11/26/2021

DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?

Generative Adversarial Networks (GANs) are among the most popular approa...
02/24/2022

Bounding Membership Inference

Differential Privacy (DP) is the de facto standard for reasoning about t...
10/23/2020

Differentially Private Learning Does Not Bound Membership Inference

Training machine learning models on privacy-sensitive data has become a ...
06/11/2021

A Shuffling Framework for Local Differential Privacy

ldp deployments are vulnerable to inference attacks as an adversary can ...
09/11/2020

MACE: A Flexible Framework for Membership Privacy Estimation in Generative Models

Generative models are widely used for publishing synthetic datasets. Des...