Differential privacy for the analyst via private equilibrium computation

DOI10.1145/2488608.2488651MaRDI QIDQ5495804zbMATH OpenOpenAlexFDO

Authors Justin Hsu, Aaron Roth, Jonathan Ullman

Publication date 7 August 2014

Published in Proceedings of the forty-eighth annual ACM symposium on Theory of Computing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1211.0877

zbMATH Keywords

analyst privacyBregman projectiondifferential privacyno-regret learningzero-sum game

Mathematics Subject Classification ID

Database theory (68P15) 2-person games (91A05) Applications of game theory (91A80) Authentication, digital signatures and secret sharing (94A62)

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.

Recommendations

• The algorithmic foundations of differential privacy
• Universally utility-maximizing privacy mechanisms
• Universally utility-maximizing privacy mechanisms
• Differential Privacy
• A statistical framework for differential privacy

Cited in

(5)

• Differentially private distributed algorithms for stochastic aggregative games
• Computing payoff allocations in the approximate core of linear programming games in a privacy-preserving manner
• Concurrent composition of differential privacy
• Private matchings and allocations
• Mirror descent algorithms with nearly dimension-independent rates for differentially-private stochastic saddle-point problems

This page was built for publication: Differential privacy for the analyst via private equilibrium computation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5495804)