Dual Query: Practical Private Query Release for High Dimensional Data

Main Article Content

Marco Gaboardi
Emilio Jesús Gallego Arias
https://orcid.org/0000-0002-9299-1192
Justin Hsu
https://orcid.org/0000-0002-8953-7060
Aaron Roth
Zhiwei Steven Wu

Abstract

We present a practical, differentially private algorithm for answering a large number of queries on high dimensional datasets. Like all algorithms for this task, ours necessarily has worst-case complexity exponential in the dimension of the data. However, our algorithm packages the computationally hard step into a concisely defined integer program, which can be solved non-privately using standard solvers. We prove accuracy and privacy theorems for our algorithm, and then demonstrate experimentally that our algorithm performs well in practice. For example, our algorithm can efficiently and accurately answer millions of queries on the Netflix dataset, which has over 17,000 attributes; this is an improvement on the state of the art by multiple orders of magnitude.

Article Details

How to Cite
Gaboardi, Marco, Emilio Gallego Arias, Justin Hsu, Aaron Roth, and Zhiwei Wu. 2017. “Dual Query: Practical Private Query Release for High Dimensional Data”. Journal of Privacy and Confidentiality 7 (2). https://doi.org/10.29012/jpc.v7i2.650.
Section
Articles

Funding data