Cactus Mechanisms: Optimal Differential Privacy Mechanisms in the Large-Composition Regime

06/25/2022
by   Wael Alghamdi, et al.
0

Most differential privacy mechanisms are applied (i.e., composed) numerous times on sensitive data. We study the design of optimal differential privacy mechanisms in the limit of a large number of compositions. As a consequence of the law of large numbers, in this regime the best privacy mechanism is the one that minimizes the Kullback-Leibler divergence between the conditional output distributions of the mechanism given two different inputs. We formulate an optimization problem to minimize this divergence subject to a cost constraint on the noise. We first prove that additive mechanisms are optimal. Since the optimization problem is infinite dimensional, it cannot be solved directly; nevertheless, we quantize the problem to derive near-optimal additive mechanisms that we call "cactus mechanisms" due to their shape. We show that our quantization approach can be arbitrarily close to an optimal mechanism. Surprisingly, for quadratic cost, the Gaussian mechanism is strictly sub-optimal compared to this cactus mechanism. Finally, we provide numerical results which indicate that cactus mechanism outperforms the Gaussian mechanism for a finite number of compositions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/20/2022

Shuffle Gaussian Mechanism for Differential Privacy

We study Gaussian mechanism in the shuffle model of differential privacy...
research
04/25/2023

Differential Privacy via Distributionally Robust Optimization

In recent years, differential privacy has emerged as the de facto standa...
research
02/05/2020

A workload-adaptive mechanism for linear queries under local differential privacy

We propose a new mechanism to accurately answer a user-provided set of l...
research
10/02/2017

Constrained Differential Privacy for Count Data

Concern about how to aggregate sensitive user data without compromising ...
research
06/28/2020

Differential Privacy of Hierarchical Census Data: An Optimization Approach

This paper is motivated by applications of a Census Bureau interested in...
research
03/30/2023

Infinite Horizon Privacy in Networked Control Systems: Utility/Privacy Tradeoffs and Design Tools

We address the problem of synthesizing distorting mechanisms that maximi...
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,...

Please sign up or login with your details

Forgot password? Click here to reset