DeepAI AI Chat
Log In Sign Up

Rényi Differential Privacy Mechanisms for Posterior Sampling

10/02/2017
by   Joseph Geumlek, et al.
University of California, San Diego
0

Using a recently proposed privacy definition of Rényi Differential Privacy (RDP), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We exploit the impact of the prior distribution in mitigating the influence of individual data points. In particular, we focus on sampling from an exponential family and specific generalized linear models, such as logistic regression. We propose novel RDP mechanisms as well as offering a new RDP analysis for an existing method in order to add value to the RDP framework. Each method is capable of achieving arbitrary RDP privacy guarantees, and we offer experimental results of their efficacy.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/05/2013

Bayesian Differential Privacy through Posterior Sampling

Differential privacy formalises privacy-preserving mechanisms that provi...
10/03/2021

Differential Privacy of Dirichlet Posterior Sampling

Besides the Laplace distribution and the Gaussian distribution, there ar...
08/02/2019

Differential Privacy for Sparse Classification Learning

In this paper, we present a differential privacy version of convex and n...
07/03/2023

Thompson Sampling under Bernoulli Rewards with Local Differential Privacy

This paper investigates the problem of regret minimization for multi-arm...
02/24/2021

Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT

The recently proposed Fast Fourier Transform (FFT)-based accountant for ...
09/09/2019

A New Analysis of Differential Privacy's Generalization Guarantees

We give a new proof of the "transfer theorem" underlying adaptive data a...
11/01/2016

Variational Bayes In Private Settings (VIPS)

We provide a general framework for privacy-preserving variational Bayes ...