Differential Privacy of Dirichlet Posterior Sampling

10/03/2021
by   Donlapark Ponnoprat, et al.
0

Besides the Laplace distribution and the Gaussian distribution, there are many more probability distributions which is not well-understood in terms of privacy-preserving property of a random draw – one of which is the Dirichlet distribution. In this work, we study the inherent privacy of releasing a single draw from a Dirichlet posterior distribution. As a complement to the previous study that provides general theories on the differential privacy of posterior sampling from exponential families, this study focuses specifically on the Dirichlet posterior sampling and its privacy guarantees. With the notion of truncated concentrated differential privacy (tCDP), we are able to derive a simple privacy guarantee of the Dirichlet posterior sampling, which effectively allows us to analyze its utility in various settings. Specifically, we prove accuracy guarantees of private Multinomial-Dirichlet sampling, which is prevalent in Bayesian tasks, and private release of a normalized histogram. In addition, with our results, it is possible to make Bayesian reinforcement learning differentially private by modifying the Dirichlet sampling for state transition probabilities.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/05/2013

Bayesian Differential Privacy through Posterior Sampling

Differential privacy formalises privacy-preserving mechanisms that provi...
research
03/23/2016

On the Theory and Practice of Privacy-Preserving Bayesian Data Analysis

Bayesian inference has great promise for the privacy-preserving analysis...
research
10/02/2017

Rényi Differential Privacy Mechanisms for Posterior Sampling

Using a recently proposed privacy definition of Rényi Differential Priva...
research
06/24/2018

On The Differential Privacy of Thompson Sampling With Gaussian Prior

We show that Thompson Sampling with Gaussian Prior as detailed by Algori...
research
10/31/2016

Bayesian Adaptive Data Analysis Guarantees from Subgaussianity

The new field of adaptive data analysis seeks to provide algorithms and ...
research
02/26/2015

Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo

We consider the problem of Bayesian learning on sensitive datasets and p...
research
06/19/2023

Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy

When releasing outputs from confidential data, agencies need to balance ...

Please sign up or login with your details

Forgot password? Click here to reset