A rate-disortion perspective on local differential privacy

Anand D. Sarwate, Lalitha Sankar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Scopus citations

Abstract

Local differential privacy is a model for privacy in which an untrusted statistician collects data from individuals who mask their data before revealing it. While randomized response has shown to be a good strategy when the statistician's goal is to estimate a parameter of the population, we consider instead the problem of locally private data publishing, in which the data collector must publish a version of the data it has collected. We model utility by a distortion measure and consider privacy mechanisms that act via a memoryless channnel operating on the data. If we consider a the source distribution to be unknown but in a class of distributions, we arrive at a robust-rate distortion model for the privacy-distortion tradeoff. We show that under Hamming distortions, the differential privacy risk is lower bounded for all nontrivial distortions, and that the lower bound grows logarithmically in the alphabet size.

Original languageEnglish (US)
Title of host publication2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages903-908
Number of pages6
ISBN (Electronic)9781479980093
DOIs
StatePublished - Jan 30 2014
Event2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014 - Monticello, United States
Duration: Sep 30 2014Oct 3 2014

Publication series

Name2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014

Other

Other2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014
CountryUnited States
CityMonticello
Period9/30/1410/3/14

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint Dive into the research topics of 'A rate-disortion perspective on local differential privacy'. Together they form a unique fingerprint.

  • Cite this

    Sarwate, A. D., & Sankar, L. (2014). A rate-disortion perspective on local differential privacy. In 2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014 (pp. 903-908). [7028550] (2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ALLERTON.2014.7028550