Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead

06/08/2021
by   Badih Ghazi, et al.
0

Differential privacy (DP) is a formal notion for quantifying the privacy loss of algorithms. Algorithms in the central model of DP achieve high accuracy but make the strongest trust assumptions whereas those in the local DP model make the weakest trust assumptions but incur substantial accuracy loss. The shuffled DP model (Bittau et al., 2017; Erlingsson et al., 2019; Cheu et al., 2019) has recently emerged as a feasible middle ground between the central and local models, providing stronger trust assumptions than the former while promising higher accuracies than the latter. In this paper, we obtain practical communication-efficient algorithms in the shuffled DP model for two basic aggregation primitives used in machine learning: 1) binary summation, and 2) histograms over a moderate number of buckets. Our algorithms achieve accuracy that is arbitrarily close to that of central DP algorithms with an expected communication per user essentially matching what is needed without any privacy constraints! We demonstrate the practicality of our algorithms by experimentally comparing their performance to several widely-used protocols such as Randomized Response (Warner, 1965) and RAPPOR (Erlingsson et al., 2014).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/05/2021

Numerical Composition of Differential Privacy

We give a fast algorithm to optimally compose privacy guarantees of diff...
research
02/03/2020

Private Summation in the Multi-Message Shuffle Model

The shuffle model of differential privacy (Erlingsson et al. SODA 2019; ...
research
06/12/2022

Distributed Differential Privacy in Multi-Armed Bandits

We consider the standard K-armed bandit problem under a distributed trus...
research
07/04/2021

Smoothed Differential Privacy

Differential privacy (DP) is a widely-accepted and widely-applied notion...
research
09/03/2023

Privacy-Utility Tradeoff of OLS with Random Projections

We study the differential privacy (DP) of a core ML problem, linear ordi...
research
04/19/2023

A global accuracy characterisation of trust

Dorst et al. (2021) put forward a deference principle called Total Trust...
research
11/29/2018

The Power of The Hybrid Model for Mean Estimation

In this work we explore the power of the hybrid model of differential pr...

Please sign up or login with your details

Forgot password? Click here to reset