Answering Summation Queries for Numerical Attributes under Differential Privacy

TL;DR

This paper investigates how to accurately answer multiple sum queries on numerical data while preserving differential privacy, highlighting the limitations of traditional methods and proposing more rigorous, low-error algorithms.

Contribution

It introduces a novel approach that improves the accuracy of sum query responses under differential privacy for numerical domains, surpassing traditional techniques.

Findings

Traditional methods are often suboptimal for numerical sum queries under differential privacy.

A new rigorous algorithm achieves lower error in answering sum queries.

The approach enhances privacy-preserving data analysis accuracy.

Abstract

In this work we explore the problem of answering a set of sum queries under Differential Privacy. This is a little understood, non-trivial problem especially in the case of numerical domains. We show that traditional techniques from the literature are not always the best choice and a more rigorous approach is necessary to develop low error algorithms.