Differential Privacy for the Analyst via Private Equilibrium Computation

TL;DR

This paper introduces mechanisms for answering many queries from multiple analysts on a private database, ensuring differential privacy for both individuals and analysts, even under collusion, with nearly optimal error rates.

Contribution

It presents the first mechanisms providing differential privacy on the joint distribution over analysts' answers, extending to non-linear queries and modeling the problem as a two-player zero-sum game.

Findings

Achieves nearly optimal error rates in some settings.

Ensures privacy even if analysts collude or have multiple accounts.

Extends techniques to handle non-linear queries.

Abstract

We give new mechanisms for answering exponentially many queries from multiple analysts on a private database, while protecting differential privacy both for the individuals in the database and for the analysts. That is, our mechanism's answer to each query is nearly insensitive to changes in the queries asked by other analysts. Our mechanism is the first to offer differential privacy on the joint distribution over analysts' answers, providing privacy for data analysts even if the other data analysts collude or register multiple accounts. In some settings, we are able to achieve nearly optimal error rates (even compared to mechanisms which do not offer analyst privacy), and we are able to extend our techniques to handle non-linear queries. Our analysis is based on a novel view of the private query-release problem as a two-player zero-sum game, which may be of independent interest.