DPCube: Differentially Private Histogram Release through Multidimensional Partitioning

TL;DR

This paper introduces DPCube, a method for releasing differentially private histograms using multidimensional partitioning strategies, including a novel kd-tree approach, to improve utility in answering linear queries.

Contribution

It proposes a new 2-phase kd-tree based partitioning strategy for differentially private histogram release, enhancing accuracy over baseline methods.

Findings

The kd-tree approach achieves lower error in counting queries.

Experimental results show improved utility in classification and record linkage tasks.

The method guarantees differential privacy while maintaining high data utility.

Abstract

Differential privacy is a strong notion for protecting individual privacy in privacy preserving data analysis or publishing. In this paper, we study the problem of differentially private histogram release for random workloads. We study two multidimensional partitioning strategies including: 1) a baseline cell-based partitioning strategy for releasing an equi-width cell histogram, and 2) an innovative 2-phase kd-tree based partitioning strategy for releasing a v-optimal histogram. We formally analyze the utility of the released histograms and quantify the errors for answering linear queries such as counting queries. We formally characterize the property of the input data that will guarantee the optimality of the algorithm. Finally, we implement and experimentally evaluate several applications using the released histograms, including counting queries, classification, and blocking for record linkage and show the benefit of our approach.