Optimal Local Bayesian Differential Privacy over Markov Chains

06/22/2022
by   Darshan Chakrabarti, et al.
0

In the literature of data privacy, differential privacy is the most popular model. An algorithm is differentially private if its outputs with and without any individual's data are indistinguishable. In this paper, we focus on data generated from a Markov chain and argue that Bayesian differential privacy (BDP) offers more meaningful guarantees in this context. Our main theoretical contribution is providing a mechanism for achieving BDP when data is drawn from a binary Markov chain. We improve on the state-of-the-art BDP mechanism and show that our mechanism provides the optimal noise-privacy tradeoffs for any local mechanism up to negligible factors. We also briefly discuss a non-local mechanism which adds correlated noise. Lastly, we perform experiments on synthetic data that detail when DP is insufficient, and experiments on real data to show that our privacy guarantees are robust to underlying distributions that are not simple Markov chains.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/29/2019

Differentially Private Markov Chain Monte Carlo

Recent developments in differentially private (DP) machine learning and ...
research
02/07/2022

Differential Privacy for Symbolic Systems with Application to Markov Chains

Data-driven systems are gathering increasing amounts of data from users,...
research
10/25/2022

Differentially Private Language Models for Secure Data Sharing

To protect the privacy of individuals whose data is being shared, it is ...
research
03/31/2023

On Rényi Differential Privacy in Statistics-Based Synthetic Data Generation

Privacy protection with synthetic data generation often uses differentia...
research
04/03/2022

Exact Privacy Guarantees for Markov Chain Implementations of the Exponential Mechanism with Artificial Atoms

Implementations of the exponential mechanism in differential privacy oft...
research
03/13/2016

Pufferfish Privacy Mechanisms for Correlated Data

Many modern databases include personal and sensitive correlated data, su...
research
01/25/2023

Efficiency in local differential privacy

We develop a theory of asymptotic efficiency in regular parametric model...

Please sign up or login with your details

Forgot password? Click here to reset