Differential Privacy Over Riemannian ManifoldsDownload PDF

21 May 2021, 20:47 (edited 21 Jan 2022)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: Differential Privacy, Riemannian Manifolds, Fréchet Mean, Laplace Mechanism, K-Norm Mechanism
  • TL;DR: We provide a mechanism for achieving differential privacy over Riemannian manifolds alongside sensitivity and utility guarantees for the Fréchet mean.
  • Abstract: In this work we consider the problem of releasing a differentially private statistical summary that resides on a Riemannian manifold. We present an extension of the Laplace or K-norm mechanism that utilizes intrinsic distances and volumes on the manifold. We also consider in detail the specific case where the summary is the Fr\'echet mean of data residing on a manifold. We demonstrate that our mechanism is rate optimal and depends only on the dimension of the manifold, not on the dimension of any ambient space, while also showing how ignoring the manifold structure can decrease the utility of the sanitized summary. We illustrate our framework in two examples of particular interest in statistics: the space of symmetric positive definite matrices, which is used for covariance matrices, and the sphere, which can be used as a space for modeling discrete distributions.
  • Supplementary Material: pdf
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: zip
15 Replies