Non-stochastic hypothesis testing for privacy
Source TitleIET Information Security
PublisherInstitution of Engineering and Technology
University of Melbourne Author/sFarokhi, Farhad
AffiliationElectrical and Electronic Engineering
Document TypeJournal Article
CitationsFarokhi, F. (2020). Non-stochastic hypothesis testing for privacy. IET Information Security, 14 (6), pp.754-763. https://doi.org/10.1049/iet-ifs.2020.0223.
Access StatusOpen Access
In this paper, we consider privacy against hypothesis testing adversaries within a non-stochastic framework. We develop a theory of non-stochastic hypothesis testing by borrowing the notion of uncertain variables from non-stochastic information theory. We define tests as binary-valued mappings on uncertain variables and prove a fundamental bound on the best performance of tests in non-stochastic hypothesis testing. We provide parallels between stochastic and non-stochastic hypothesis-testing frameworks. We use the performance bound in non-stochastic hypothesis testing to develop a measure of privacy. We then construct reporting policies with prescribed privacy and utility guarantees. The utility of a reporting policy is measured by the distance between the reported and original values. Finally, we present the notion of indistinguishability as a measure of privacy by extending identifiability from the privacy literature to the non-stochastic framework. We prove that linear quantizers can indeed achieve identifiability for responding to linear queries on private datasets.
- Click on "Export Reference in RIS Format" and choose "open with... Endnote".
- Click on "Export Reference in RIS Format". Login to Refworks, go to References => Import References