DeepAI AI Chat
Log In Sign Up

Differential privacy for symmetric log-concave mechanisms

by   Staal A. Vinterbo, et al.

Adding random noise to database query results is an important tool for achieving privacy. A challenge is to minimize this noise while still meeting privacy requirements. Recently, a sufficient and necessary condition for (ϵ, δ)-differential privacy for Gaussian noise was published. This condition allows the computation of the minimum privacy-preserving scale for this distribution. We extend this work and provide a sufficient and necessary condition for (ϵ, δ)-differential privacy for all symmetric and log-concave noise densities. Our results allow fine-grained tailoring of the noise distribution to the dimensionality of the query result. We demonstrate that this can yield significantly lower mean squared errors than those incurred by the currently used Laplace and Gaussian mechanisms for the same ϵ and δ.


page 1

page 2

page 3

page 4


Grafting Laplace and Gaussian distributions: A new noise mechanism for differential privacy

The framework of Differential privacy protects an individual's privacy w...

A closed form scale bound for the (ε, δ)-differentially private Gaussian Mechanism valid for all privacy regimes

The standard closed form lower bound on σ for providing (ϵ, δ)-different...

Gaussian Noise is Nearly Instance Optimal for Private Unbiased Mean Estimation

We investigate unbiased high-dimensional mean estimators in differential...

Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability

Voting plays a central role in bringing crowd wisdom to collective decis...

MVG Mechanism: Differential Privacy under Matrix-Valued Query

Differential privacy mechanism design has traditionally been tailored fo...

Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning

We study the privacy risks that are associated with training a neural ne...

A Differential Privacy Mechanism Design Under Matrix-Valued Query

Traditionally, differential privacy mechanism design has been tailored f...

Code Repositories


Algorithm for computing the Subbotin noise scale for (eps, del)-differential privacy

view repo