Optimal error of query sets under the differentially-private matrix mechanism - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year :

Optimal error of query sets under the differentially-private matrix mechanism

Abstract

A common goal of privacy research is to release synthetic data that satisfies a formal privacy guarantee and can be used by an analyst in place of the original data. To achieve reasonable accuracy, a synthetic data set must be tuned to support a specified set of queries accurately, sacrificing fidelity for other queries. This work considers methods for producing synthetic data under differential privacy and investigates what makes a set of queries "easy" or "hard" to answer. We consider answering sets of linear counting queries using the matrix mechanism, a recent differentially-private mechanism that can reduce error by adding complex correlated noise adapted to a specified workload. Our main result is a novel lower bound on the minimum total error required to simultaneously release answers to a set of workload queries. The bound reveals that the hardness of a query workload is related to the spectral properties of the workload when it is represented in matrix form. The bound is most informative for $(\epsilon,\delta)$-differential privacy but also applies to $\epsilon$-differential privacy.

Dates and versions

hal-00878876 , version 1 (31-10-2013)

Identifiers

Cite

Chao Li, Gerome Miklau. Optimal error of query sets under the differentially-private matrix mechanism. 2012. ⟨hal-00878876⟩
72 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More