Emergent Mind

Local Mutual-Information Differential Privacy

(2405.07596)
Published May 13, 2024 in cs.IT and math.IT

Abstract

Local mutual-information differential privacy (LMIDP) is a privacy notion that aims to quantify the reduction of uncertainty about the input data when the output of a privacy-preserving mechanism is revealed. We study the relation of LMIDP with local differential privacy (LDP), the de facto standard notion of privacy in context-independent (CI) scenarios, and with local information privacy (LIP), the state-of-the-art notion for context-dependent settings. We establish explicit conversion rules, i.e., bounds on the privacy parameters for a LMIDP mechanism to also satisfy LDP/LIP, and vice versa. We use our bounds to formally verify that LMIDP is a weak privacy notion. We also show that uncorrelated Gaussian noise is the best-case noise in terms of CI-LMIDP if both the input data and the noise are subject to an average power constraint.

We're not able to analyze this paper right now due to high demand.

Please check back later (sorry!).

Generate a summary of this paper on our Pro plan:

We ran into a problem analyzing this paper.

Newsletter

Get summaries of trending comp sci papers delivered straight to your inbox:

Unsubscribe anytime.