PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning

by   Seng Pei Liew, et al.

We propose a new framework of synthesizing data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion, such that training deep generative models is possible without re-using the original data. Hence, no extra privacy costs or model constraints are incurred, in contrast to popular approaches such as Differentially Private Stochastic Gradient Descent (DP-SGD), which, among other issues, causes degradation in privacy guarantees as the training iteration increases. We demonstrate a realization of our framework by making use of the characteristic function and an adversarial re-weighting objective, which are of independent interest as well. Our proposal has theoretical guarantees of performance, and empirical evaluations on multiple datasets show that our approach outperforms other methods at reasonable levels of privacy.



There are no comments yet.


page 8

page 20

page 21

page 23


Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence

Although machine learning models trained on massive data have led to bre...

Differentially Private Generative Adversarial Networks with Model Inversion

To protect sensitive data in training a Generative Adversarial Network (...

Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty

We show that differentially private stochastic gradient descent (DP-SGD)...

Improving Differentially Private Models with Active Learning

Broad adoption of machine learning techniques has increased privacy conc...

A Differentially Private Multi-Output Deep Generative Networks Approach For Activity Diary Synthesis

In this work, we develop a privacy-by-design generative model for synthe...

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

The wide-spread availability of rich data has fueled the growth of machi...

Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data

Open data plays a fundamental role in the 21th century by stimulating ec...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.