DeepAI AI Chat
Log In Sign Up

A bounded-noise mechanism for differential privacy

by   Yuval Dagan, et al.

Answering multiple counting queries is one of the best-studied problems in differential privacy. Its goal is to output an approximation of the average 1/n∑_i=1^n x⃗^(i) of vectors x⃗^(i)∈ [0,1]^k, while preserving the privacy with respect to any x⃗^(i). We present an (ϵ,δ)-private mechanism with optimal ℓ_∞ error for most values of δ. This result settles the conjecture of Steinke and Ullman [2020] for the these values of δ. Our algorithm adds independent noise of bounded magnitude to each of the k coordinates, while prior solutions relied on unbounded noise such as the Laplace and Gaussian mechanisms.


page 1

page 2

page 3

page 4


The Bounded Laplace Mechanism in Differential Privacy

The Laplace mechanism is the workhorse of differential privacy, applied ...

The Bounded Gaussian Mechanism for Differential Privacy

The Gaussian mechanism is one differential privacy mechanism commonly us...

Privately Answering Counting Queries with Generalized Gaussian Mechanisms

We consider the problem of answering k counting (i.e. sensitivity-1) que...

Answering Summation Queries for Numerical Attributes under Differential Privacy

In this work we explore the problem of answering a set of sum queries un...

Noiseless Privacy

In this paper, we define noiseless privacy, as a non-stochastic rival to...

Differential privacy and noisy confidentiality concepts for European population statistics

The paper aims to give an overview of various approaches to statistical ...

Differential Privacy with Higher Utility through Non-identical Additive Noise

Differential privacy is typically ensured by perturbation with additive ...