Towards Practical Differential Privacy in Data Analysis: Understanding the Effect of Epsilon on Utility in Private ERM

06/06/2022
by   Yuzhe Li, et al.
0

In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method. We take the first step towards solving the above problem by theoretically exploring the effect of epsilon (the parameter of differential privacy that determines the strength of privacy guarantee) on utility of the learning model. We trace the change of utility with modification of epsilon and reveal an established relationship between epsilon and utility. We then formalize this relationship and propose a practical approach for estimating the utility under an arbitrary value of epsilon. Both theoretical analysis and experimental results demonstrate high estimation accuracy and broad applicability of our approach in practical applications. As providing algorithms with strong utility guarantees that also give privacy when possible becomes more and more accepted, our approach would have high practical value and may be likely to be adopted by companies and organizations that would like to preserve privacy but are unwilling to compromise on utility.

READ FULL TEXT

page 10

page 11

page 13

research
12/05/2019

Element Level Differential Privacy: The Right Granularity of Privacy

Differential Privacy (DP) provides strong guarantees on the risk of comp...
research
06/07/2020

BUDS: Balancing Utility and Differential Privacy by Shuffling

Balancing utility and differential privacy by shuffling or BUDS is an ap...
research
11/28/2022

On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation

Devising procedures for auditing generative model privacy-utility tradeo...
research
11/02/2020

the Connection between Cryptography and Differential Privacy: a Survey

Due to the successful application of data analysis technology in many fi...
research
09/29/2022

L-SRR: Local Differential Privacy for Location-Based Services with Staircase Randomized Response

Location-based services (LBS) have been significantly developed and wide...
research
03/22/2018

Locally Private Bayesian Inference for Count Models

As more aspects of social interaction are digitally recorded, there is a...
research
08/01/2022

On Shapley Value in Data Assemblage Under Independent Utility

In many applications, an organization may want to acquire data from many...

Please sign up or login with your details

Forgot password? Click here to reset