Non-Stochastic Hypothesis Testing with Application to Privacy Against Hypothesis-Testing Adversaries
Source TitleProceedings of the ... IEEE Conference on Decision & Control / IEEE Control Systems Society. IEEE Conference on Decision & Control
University of Melbourne Author/sFarokhi, Farhad
AffiliationElectrical and Electronic Engineering
Document TypeConference Paper
CitationsFarokhi, F. (2020). Non-Stochastic Hypothesis Testing with Application to Privacy Against Hypothesis-Testing Adversaries. Proceedings of the 2019 IEEE 58th Conference on Decision and Control (CDC), 2019-December, pp.6118-6123. IEEE. https://doi.org/10.1109/CDC40024.2019.9029652.
Access StatusOpen Access
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 performance of tests in non-stochastic hypothesis testing. We use this bound 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 reported and original values. We illustrate the effects of using such privacy-preserving reporting polices on a publicly- available practical dataset of preferences and demographics of young individuals with Slovakian nationality.
- 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