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

by   Wael Alghamdi, et al.

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.


page 1

page 2

page 3

page 4


Shuffle Gaussian Mechanism for Differential Privacy

We study Gaussian mechanism in the shuffle model of differential privacy...

Optimal Noise-Adding Mechanism in Additive Differential Privacy

We derive the optimal (0, δ)-differentially private query-output indepen...

Constrained Differential Privacy for Count Data

Concern about how to aggregate sensitive user data without compromising ...

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...

Differential Privacy of Hierarchical Census Data: An Optimization Approach

This paper is motivated by applications of a Census Bureau interested in...

Security Versus Privacy

Linear queries can be submitted to a server containing private data. The...

Differential Privacy for Symbolic Systems with Application to Markov Chains

Data-driven systems are gathering increasing amounts of data from users,...