The Discrete Gaussian for Differential Privacy

03/31/2020

∙

by   Clement Canonne, et al.

∙

4

∙

share

We show how to efficiently provide differentially private answers to counting queries (or integer-valued low-sensitivity queries) by adding discrete Gaussian noise, with essentially the same privacy and accuracy as the continuous Gaussian. The use of a discrete distribution is necessary in practice, as finite computers cannot represent samples from continuous distributions and numerical errors may destroy the privacy guarantee.