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

by   Staal A. Vinterbo, et al.

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.


page 1

page 2

page 3

page 4


Differential privacy for symmetric log-concave mechanisms

Adding random noise to database query results is an important tool for a...

Rényi Differential Privacy of the Sampled Gaussian Mechanism

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and ...

Gaussian Noise is Nearly Instance Optimal for Private Unbiased Mean Estimation

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

The Discrete Gaussian for Differential Privacy

We show how to efficiently provide differentially private answers to cou...

An MMSE Lower Bound via Poincaré Inequality

This paper studies the minimum mean squared error (MMSE) of estimating 𝐗...

A Central Limit Theorem for Differentially Private Query Answering

Perhaps the single most important use case for differential privacy is t...

Sharp phase transitions for exact support recovery under local differential privacy

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