Local Private Hypothesis Testing: Chi-Square Tests

Marco Gaboardi, Ryan Rogers
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:1626-1635, 2018.

Abstract

The local model for differential privacy is emerging as the reference model for practical applications of collecting and sharing sensitive information while satisfying strong privacy guarantees. In the local model, there is no trusted entity which is allowed to have each individual’s raw data as is assumed in the traditional curator model. Individuals’ data are usually perturbed before sharing them. We explore the design of private hypothesis tests in the local model, where each data entry is perturbed to ensure the privacy of each participant. Specifically, we analyze locally private chi-square tests for goodness of fit and independence testing.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-gaboardi18a, title = {Local Private Hypothesis Testing: {C}hi-Square Tests}, author = {Gaboardi, Marco and Rogers, Ryan}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {1626--1635}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/gaboardi18a/gaboardi18a.pdf}, url = {http://proceedings.mlr.press/v80/gaboardi18a.html}, abstract = {The local model for differential privacy is emerging as the reference model for practical applications of collecting and sharing sensitive information while satisfying strong privacy guarantees. In the local model, there is no trusted entity which is allowed to have each individual’s raw data as is assumed in the traditional curator model. Individuals’ data are usually perturbed before sharing them. We explore the design of private hypothesis tests in the local model, where each data entry is perturbed to ensure the privacy of each participant. Specifically, we analyze locally private chi-square tests for goodness of fit and independence testing.} }
Endnote
%0 Conference Paper %T Local Private Hypothesis Testing: Chi-Square Tests %A Marco Gaboardi %A Ryan Rogers %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-gaboardi18a %I PMLR %P 1626--1635 %U http://proceedings.mlr.press/v80/gaboardi18a.html %V 80 %X The local model for differential privacy is emerging as the reference model for practical applications of collecting and sharing sensitive information while satisfying strong privacy guarantees. In the local model, there is no trusted entity which is allowed to have each individual’s raw data as is assumed in the traditional curator model. Individuals’ data are usually perturbed before sharing them. We explore the design of private hypothesis tests in the local model, where each data entry is perturbed to ensure the privacy of each participant. Specifically, we analyze locally private chi-square tests for goodness of fit and independence testing.
APA
Gaboardi, M. & Rogers, R.. (2018). Local Private Hypothesis Testing: Chi-Square Tests. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:1626-1635 Available from http://proceedings.mlr.press/v80/gaboardi18a.html.

Related Material