CRFeb 24, 2017

Renyi Differential Privacy

arXiv:1702.07476v31526 citations
Originality Incremental advance
AI Analysis

This work provides a new privacy definition for data analysis, offering incremental improvements in analyzing privacy guarantees.

The paper introduces Renyi Differential Privacy as a relaxation of differential privacy using Renyi divergence, which enables tighter analysis of composite heterogeneous mechanisms.

We propose a natural relaxation of differential privacy based on the Renyi divergence. Closely related notions have appeared in several recent papers that analyzed composition of differentially private mechanisms. We argue that the useful analytical tool can be used as a privacy definition, compactly and accurately representing guarantees on the tails of the privacy loss. We demonstrate that the new definition shares many important properties with the standard definition of differential privacy, while additionally allowing tighter analysis of composite heterogeneous mechanisms.

Code Implementations2 repos
Foundations

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

Your Notes