Locating a Small Cluster Privately

TL;DR

This paper introduces a novel differentially private algorithm for locating small clusters, enhancing private data analysis and relaxing existing privacy-preserving techniques for broader application.

Contribution

It presents a new clustering algorithm that improves privacy guarantees and simplifies the integration of non-private analyses into differentially private frameworks.

Findings

Effective in locating small clusters privately

Reduces complexity of privacy-preserving data analysis

Enhances the utility of differential privacy in practical scenarios

Abstract

We present a new algorithm for locating a small cluster of points with differential privacy [Dwork, McSherry, Nissim, and Smith, 2006]. Our algorithm has implications to private data exploration, clustering, and removal of outliers. Furthermore, we use it to significantly relax the requirements of the sample and aggregate technique [Nissim, Raskhodnikova, and Smith, 2007], which allows compiling of "off the shelf" (non-private) analyses into analyses that preserve differential privacy.