English

BUDS: Balancing Utility and Differential Privacy by Shuffling

Machine Learning 2020-06-09 v1 Cryptography and Security Machine Learning

Abstract

Balancing utility and differential privacy by shuffling or \textit{BUDS} is an approach towards crowd-sourced, statistical databases, with strong privacy and utility balance using differential privacy theory. Here, a novel algorithm is proposed using one-hot encoding and iterative shuffling with the loss estimation and risk minimization techniques, to balance both the utility and privacy. In this work, after collecting one-hot encoded data from different sources and clients, a step of novel attribute shuffling technique using iterative shuffling (based on the query asked by the analyst) and loss estimation with an updation function and risk minimization produces a utility and privacy balanced differential private report. During empirical test of balanced utility and privacy, BUDS produces ϵ=0.02\epsilon = 0.02 which is a very promising result. Our algorithm maintains a privacy bound of ϵ=ln[t/((n11)S)]\epsilon = ln [t/((n_1 - 1)^S)] and loss bound of celn[t/((n11)S)]1c' \bigg|e^{ln[t/((n_1 - 1)^S)]} - 1\bigg|.

Keywords

Cite

@article{arxiv.2006.04125,
  title  = {BUDS: Balancing Utility and Differential Privacy by Shuffling},
  author = {Poushali Sengupta and Sudipta Paul and Subhankar Mishra},
  journal= {arXiv preprint arXiv:2006.04125},
  year   = {2020}
}

Comments

11 pages, 3 images, 3 tables, Accepted to 11th ICCCNT, 2020, IIT KGP

R2 v1 2026-06-23T16:07:28.963Z