Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Workshop on Distributed and Private Machine Learning

Distributed Gaussian Differential Privacy Via Shuffling

Kan Chen · Qi Long


Abstract: Traditionally, there are two models for implementing differential privacy: local model and centralized model. \emph{Shuffled model} is a relatively new model that aims to provide greater accuracy while preserving privacy by shuffling batches of similar data. In this paper, we consider the analytic privacy study of a \emph{shuffled model} for f-differential privacy''(f-DP), a new relaxation of traditional (ϵ,δ)-differential privacy. We provide a powerful technique to import the existing \emph{shuffled model} results proven for the (ϵ,δ)-DP to f-DP, with which we derive a simple and easy-to-interpret theorem of privacy amplification by shuffling for f-DP. Furthermore, we prove that compared with the original \emph{shuffled model} from \cite{cheu2019distributed}, f-DP provides a tighter upper bound in terms of the privacy analysis of sum queries. The approach of f-DP can be applied to broader classes of models to achieve more accurate privacy analysis

Chat is not available.