Differentially Private Synthetic Data Using KD-Trees

TL;DR

This paper introduces space partitioning methods combined with noise perturbation to generate differentially private synthetic data, offering transparent algorithms with improved utility and scalability over deep generative models.

Contribution

It presents novel data independent and data dependent algorithms using space partitioning for differentially private synthetic data generation, overcoming high-dimensional challenges.

Findings

Empirical utility improvements over prior methods

Theoretical analysis of utility-privacy trade-offs

Scalable algorithms effective in high dimensions

Abstract

Creation of a synthetic dataset that faithfully represents the data distribution and simultaneously preserves privacy is a major research challenge. Many space partitioning based approaches have emerged in recent years for answering statistical queries in a differentially private manner. However, for synthetic data generation problem, recent research has been mainly focused on deep generative models. In contrast, we exploit space partitioning techniques together with noise perturbation and thus achieve intuitive and transparent algorithms. We propose both data independent and data dependent algorithms for $\epsilon$-differentially private synthetic data generation whose kernel density resembles that of the real dataset. Additionally, we provide theoretical results on the utility-privacy trade-offs and show how our data dependent approach overcomes the curse of dimensionality and leads to a scalable algorithm. We show empirical utility improvements over the prior work, and discuss performance of our algorithm on a downstream classification task on a real dataset.