$α$-leakage by Rényi Divergence and Sibson Mutual Information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Ni, Zarrabian, Mohammad Amin, Sadeghi, Parastoo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909240310890496
author Ding, Ni
Zarrabian, Mohammad Amin
Sadeghi, Parastoo
author_facet Ding, Ni
Zarrabian, Mohammad Amin
Sadeghi, Parastoo
contents For $\tilde{f}(t) = \exp(\frac{α-1}αt)$, this paper proposes a $\tilde{f}$-mean information gain measure. Rényi divergence is shown to be the maximum $\tilde{f}$-mean information gain incurred at each elementary event $y$ of channel output $Y$ and Sibson mutual information is the $\tilde{f}$-mean of this $Y$-elementary information gain. Both are proposed as $α$-leakage measures, indicating the most information an adversary can obtain on sensitive data. It is shown that the existing $α$-leakage by Arimoto mutual information can be expressed as $\tilde{f}$-mean measures by a scaled probability. Further, Sibson mutual information is interpreted as the maximum $\tilde{f}$-mean information gain over all estimation decisions applied to channel output.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00423
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle $α$-leakage by Rényi Divergence and Sibson Mutual Information
Ding, Ni
Zarrabian, Mohammad Amin
Sadeghi, Parastoo
Information Theory
For $\tilde{f}(t) = \exp(\frac{α-1}αt)$, this paper proposes a $\tilde{f}$-mean information gain measure. Rényi divergence is shown to be the maximum $\tilde{f}$-mean information gain incurred at each elementary event $y$ of channel output $Y$ and Sibson mutual information is the $\tilde{f}$-mean of this $Y$-elementary information gain. Both are proposed as $α$-leakage measures, indicating the most information an adversary can obtain on sensitive data. It is shown that the existing $α$-leakage by Arimoto mutual information can be expressed as $\tilde{f}$-mean measures by a scaled probability. Further, Sibson mutual information is interpreted as the maximum $\tilde{f}$-mean information gain over all estimation decisions applied to channel output.
title $α$-leakage by Rényi Divergence and Sibson Mutual Information
topic Information Theory
url https://arxiv.org/abs/2405.00423