DeepAI AI Chat
Log In Sign Up

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

12/18/2020
by   Staal A. Vinterbo, et al.
0

The standard closed form lower bound on σ for providing (ϵ, δ)-differential privacy by adding zero mean Gaussian noise with variance σ^2 is σ > Δ√(2)(ϵ^-1) √(log( 5/4δ^-1)) for ϵ∈ (0,1). We present a similar closed form bound σ≥Δ (ϵ√(2))^-1(√(az+ϵ) + s√(az)) for z=-log(4δ(1-δ)) and (a,s)=(1,1) if δ≤ 1/2 and (a,s)=(π/4,-1) otherwise. Our bound is valid for all ϵ > 0 and is always lower (better). We also present a sufficient condition for (ϵ, δ)-differential privacy when adding noise distributed according to even and log-concave densities supported everywhere.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/23/2022

Differential privacy for symmetric log-concave mechanisms

Adding random noise to database query results is an important tool for a...
08/28/2019

Rényi Differential Privacy of the Sampled Gaussian Mechanism

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and ...
01/31/2023

Gaussian Noise is Nearly Instance Optimal for Private Unbiased Mean Estimation

We investigate unbiased high-dimensional mean estimators in differential...
03/31/2020

The Discrete Gaussian for Differential Privacy

We show how to efficiently provide differentially private answers to cou...
05/12/2022

An MMSE Lower Bound via Poincaré Inequality

This paper studies the minimum mean squared error (MMSE) of estimating 𝐗...
03/15/2021

A Central Limit Theorem for Differentially Private Query Answering

Perhaps the single most important use case for differential privacy is t...
11/30/2020

Sharp phase transitions for exact support recovery under local differential privacy

We address the problem of variable selection in the Gaussian mean model ...