DeepAI
Log In Sign Up

Heavy Hitters and the Structure of Local Privacy

11/13/2017
by   Mark Bun, et al.
0

We present a new locally differentially private algorithm for the heavy hitters problem which achieves optimal worst-case error as a function of all standardly considered parameters. Prior work obtained error rates which depend optimally on the number of users, the size of the domain, and the privacy parameter, but depend sub-optimally on the failure probability. We strengthen existing lower bounds on the error to incorporate the failure probability, and show that our new upper bound is tight with respect to this parameter as well. Our lower bound is based on a new understanding of the structure of locally private protocols. We further develop these ideas to obtain the following general results beyond heavy hitters. ∙ Advanced Grouposition: In the local model, group privacy for k users degrades proportionally to ≈√(k), instead of linearly in k as in the central model. Stronger group privacy yields improved max-information guarantees, as well as stronger lower bounds (via "packing arguments"), over the central model. ∙ Building on a transformation of Bassily and Smith (STOC 2015), we give a generic transformation from any non-interactive approximate-private local protocol into a pure-private local protocol. Again in contrast with the central model, this shows that we cannot obtain more accurate algorithms by moving from pure to approximate local privacy.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/07/2018

Tight Lower Bounds for Locally Differentially Private Selection

We prove a tight lower bound (up to constant factors) on the sample comp...
06/15/2021

Locally Differentially Private Frequency Estimation

We present two new local differentially private algorithms for frequency...
11/20/2018

Locally Private Gaussian Estimation

We study a basic private estimation problem: each of n users draws a sin...
04/20/2020

Connecting Robust Shuffle Privacy and Pan-Privacy

In the shuffle model of differential privacy, data-holding users send ra...
02/05/2020

Pure Differentially Private Summation from Anonymous Messages

The shuffled (aka anonymous) model has recently generated significant in...
07/06/2022

Private Matrix Approximation and Geometry of Unitary Orbits

Consider the following optimization problem: Given n × n matrices A and ...
06/20/2022

Walking to Hide: Privacy Amplification via Random Message Exchanges in Network

The *shuffle model* is a powerful tool to amplify the privacy guarantees...