Differentially Private Empirical Risk Minimization with Input Perturbation

10/20/2017
by   Kazuto Fukuchi, et al.
0

We propose a novel framework for the differentially private ERM, input perturbation. Existing differentially private ERM implicitly assumed that the data contributors submit their private data to a database expecting that the database invokes a differentially private mechanism for publication of the learned model. In input perturbation, each data contributor independently randomizes her/his data by itself and submits the perturbed data to the database. We show that the input perturbation framework theoretically guarantees that the model learned with the randomized data eventually satisfies differential privacy with the prescribed privacy parameters. At the same time, input perturbation guarantees that local differential privacy is guaranteed to the server. We also show that the excess risk bound of the model learned with input perturbation is O(1/n) under a certain condition, where n is the sample size. This is the same as the excess risk bound of the state-of-the-art.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/11/2018

Differentially Private Confidence Intervals for Empirical Risk Minimization

The process of data mining with differential privacy produces results th...
research
05/13/2019

Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms

Differential privacy is concerned about the prediction quality while mea...
research
01/06/2022

Learning to be adversarially robust and differentially private

We study the difficulties in learning that arise from robust and differe...
research
09/06/2021

Differentially-Private Fingerprinting of Relational Databases

When sharing sensitive databases with other parties, a database owner ai...
research
08/24/2022

DP2-Pub: Differentially Private High-Dimensional Data Publication with Invariant Post Randomization

A large amount of high-dimensional and heterogeneous data appear in prac...
research
04/08/2022

Assessing Statistical Disclosure Risk for Differentially Private, Hierarchical Count Data, with Application to the 2020 U.S. Decennial Census

We propose Bayesian methods to assess the statistical disclosure risk of...

Please sign up or login with your details

Forgot password? Click here to reset