Locally Differentially-Private Randomized Response for Discrete Distribution Learning

11/29/2018
by   Adriano Pastore, et al.
0

We consider a setup in which confidential i.i.d. samples X_1,,X_n from an unknown finite-support distribution p are passed through n copies of a discrete privatization channel (a.k.a. mechanism) producing outputs Y_1,,Y_n. The channel law guarantees a local differential privacy of ϵ. Subject to a prescribed privacy level ϵ, the optimal channel should be designed such that an estimate of the source distribution based on the channel outputs Y_1,,Y_n converges as fast as possible to the exact value p. For this purpose we study the convergence to zero of three distribution distance metrics: f-divergence, mean-squared error and total variation. We derive the respective normalized first-order terms of convergence (as n→∞), which for a given target privacy ϵ represent a rule-of-thumb factor by which the sample size must be augmented so as to achieve the same estimation accuracy as that of a non-randomizing channel. We formulate the privacy-fidelity trade-off problem as being that of minimizing said first-order term under a privacy constraint ϵ. We further identify a scalar quantity that captures the essence of this trade-off, and prove bounds and data-processing inequalities on this quantity. For some specific instances of the privacy-fidelity trade-off problem, we derive inner and outer bounds on the optimal trade-off curve.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/21/2020

Fisher information under local differential privacy

We develop data processing inequalities that describe how Fisher informa...
research
05/16/2018

Accuracy-Privacy Trade-off in Analyzing Randomized Responses

We consider the problem of analyzing a global property of private data, ...
research
12/23/2020

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Th...
research
02/28/2018

INSPECTRE: Privately Estimating the Unseen

We develop differentially private methods for estimating various distrib...
research
07/08/2021

Locally differentially private estimation of nonlinear functionals of discrete distributions

We study the problem of estimating non-linear functionals of discrete di...
research
10/24/2022

Contraction of Locally Differentially Private Mechanisms

We investigate the contraction properties of locally differentially priv...
research
01/17/2020

Privacy Amplification of Iterative Algorithms via Contraction Coefficients

We investigate the framework of privacy amplification by iteration, rece...

Please sign up or login with your details

Forgot password? Click here to reset