paper-with-me

Papers

DTGAN: Differential Private Training for Tabular GANs

2021-07-06 · Aditya Kunar, Robert Birke, Zilong Zhao, Lydia Chen

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%.

📄 PDF Abstract BibTeX arXiv:2107.02521

Code (0)

등록된 구현이 없습니다.

Tasks

Attribute

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Tanh Activation 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Singular Value Clipping 설명 없음
WGAN Wasserstein GAN, or WGAN, is a type of generative adversarial network that minimizes an approximation of the Earth-Mover's distance (EM) rather than the Jensen-Shannon…
Kaiming Initialization 설명 없음
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…

Similar Papers 제목 키워드 기반

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

2023-12-20 · Zijian Li, Zhihui Wang

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 bee…

Generative Adversarial NetworkImage GenerationTabular Data Generation

Improving Correlation Capture in Generating Imbalanced Data using Differentially Private Conditional GANs

2022-06-28 · Chang Sun, Johan van Soest, Michel Dumontier

Despite the remarkable success of Generative Adversarial Networks (GANs) on text, images, and videos, generating high-quality tabular data is still under development owing to some unique challenges such as capturing depe…

Privacy PreservingSynthetic Data Generation

Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weights

2025-01-13 · Jiajia Xie, Sheng Zhang, Beihao Xia, Zhu Xiao 외

Pedestrian trajectory prediction is a critical technology in the evolution of self-driving cars toward complete artificial intelligence. Over recent years, focusing on the trajectories of pedestrians to model their socia…

Pedestrian Trajectory PredictionSelf-Driving CarsTrajectory Prediction

Generating tabular datasets under differential privacy

2023-08-28 · Gianluca Truda

Machine Learning (ML) is accelerating progress across fields and industries, but relies on accessible and high-quality training data. Some of the most important datasets are found in biomedical and financial domains in t…

Synthetic Data Generation

DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators

2024-12-03 · Tejumade Afonja, Hui-Po Wang, Raouf Kerkouche, Mario Fritz

Generating tabular data under differential privacy (DP) protection ensures theoretical privacy guarantees but poses challenges for training machine learning models, primarily due to the need to capture complex structures…

Tabular Data Generation