Cryptology ePrint Archive: Report 2016/816

Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds

Mark Bun and Thomas Steinke

Abstract: "Concentrated differential privacy" was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many privacy-preserving computations. We present an alternative formulation of the concept of concentrated differential privacy in terms of the Renyi divergence between the distributions obtained by running an algorithm on neighboring inputs. With this reformulation in hand, we prove sharper quantitative results, establish lower bounds, and raise a few new questions. We also unify this approach with approximate differential privacy by giving an appropriate definition of "approximate concentrated differential privacy."

Category / Keywords: differential privacy, lower bounds

Original Publication (in the same form): IACR-TCC B--2016

Date: received 23 Aug 2016, last revised 25 Aug 2016

Contact author: mbun at seas harvard edu, tsteinke@seas harvard edu

Available format(s): PDF | BibTeX Citation

Version: 20160826:055009 (All versions of this report)

Short URL: ia.cr/2016/816

Discussion forum: Show discussion | Start new discussion


[ Cryptology ePrint archive ]