Pure Differential Privacy for Functional Summaries via a Laplace-like Process

arXiv:2309.00125v2 Announce Type: replace-cross
Abstract: Many existing mechanisms to achieve differential privacy (DP) on infinite-dimensional functional summaries often involve embedding these summaries into finite-dimensional subspaces and applying traditional DP techniques. Such mechanisms generally treat each dimension uniformly and struggle with complex, structured summaries. This work introduces a novel mechanism for DP functional summary release: the Independent Component Laplace Process (ICLP) mechanism. This mechanism treats the summaries of interest as truly infinite-dimensional objects, thereby addressing several limitations of existing mechanisms. We …

abstract arxiv cs.cr cs.lg differential differential privacy embedding functional novel privacy process stat.ml struggle type via work