20
10

Canonical Noise Distributions and Private Hypothesis Tests

Abstract

ff-DP has recently been proposed as a generalization of differential privacy allowing a lossless analysis of composition, post-processing, and privacy amplification via subsampling. In the setting of ff-DP, we propose the concept of a canonical noise distribution (CND), the first mechanism designed for an arbitrary ff-DP guarantee. The notion of CND captures whether an additive privacy mechanism perfectly matches the privacy guarantee of a given ff. We prove that a CND always exists, and give a construction that produces a CND for any ff. We show that private hypothesis tests are intimately related to CNDs, allowing for the release of private pp-values at no additional privacy cost as well as the construction of uniformly most powerful (UMP) tests for binary data, within the general ff-DP framework. We apply our techniques to the problem of difference of proportions testing, and construct a UMP unbiased (UMPU) "semi-private" test which upper bounds the performance of any ff-DP test. Using this as a benchmark we propose a private test, based on the inversion of characteristic functions, which allows for optimal inference for the two population parameters and is nearly as powerful as the semi-private UMPU. When specialized to the case of (ϵ,0)(\epsilon,0)-DP, we show empirically that our proposed test is more powerful than any (ϵ/2)(\epsilon/\sqrt 2)-DP test and has more accurate type I errors than the classic normal approximation test.

View on arXiv
Comments on this paper

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.