CRDSITLGMay 6, 2016

Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds

arXiv:1605.02065v1977 citations
AI Analysis

This work provides incremental improvements to differential privacy methods for data analysis applications.

The paper tackles the problem of analyzing privacy-preserving computations by reformulating concentrated differential privacy using Renyi divergence, resulting in sharper quantitative results and lower bounds.

"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."

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes