Saved in:
Bibliographic Details
Main Authors: Grosse, Leonhard, Saeidian, Sara, Oechtering, Tobias J., Skoglund, Mikael
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.11473
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908676177002496
author Grosse, Leonhard
Saeidian, Sara
Oechtering, Tobias J.
Skoglund, Mikael
author_facet Grosse, Leonhard
Saeidian, Sara
Oechtering, Tobias J.
Skoglund, Mikael
contents We examine the privacy amplification of channels that do not necessarily satisfy any LDP guarantee by analyzing their contraction behavior in terms of $f_α$-divergence, an $f$-divergence related to Rényi-divergence via a monotonic transformation. We present bounds on contraction for restricted sets of prior distributions via $f$-divergence inequalities and present an improved Pinsker's inequality for $f_α$-divergence based on the joint range technique by Harremoës and Vajda. The presented bound is tight whenever the value of the total variation distance is larger than 1/$α$. By applying these inequalities in a cross-channel setting, we arrive at strong data processing inequalities for $f_α$-divergence that can be adapted to use-case specific restrictions of input distributions and channel. The application of these results to privacy amplification shows that even very sparse channels can lead to significant privacy amplification when used as a post-processing step after local differentially private mechanisms.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11473
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bounds on the privacy amplification of arbitrary channels via the contraction of $f_α$-divergence
Grosse, Leonhard
Saeidian, Sara
Oechtering, Tobias J.
Skoglund, Mikael
Information Theory
We examine the privacy amplification of channels that do not necessarily satisfy any LDP guarantee by analyzing their contraction behavior in terms of $f_α$-divergence, an $f$-divergence related to Rényi-divergence via a monotonic transformation. We present bounds on contraction for restricted sets of prior distributions via $f$-divergence inequalities and present an improved Pinsker's inequality for $f_α$-divergence based on the joint range technique by Harremoës and Vajda. The presented bound is tight whenever the value of the total variation distance is larger than 1/$α$. By applying these inequalities in a cross-channel setting, we arrive at strong data processing inequalities for $f_α$-divergence that can be adapted to use-case specific restrictions of input distributions and channel. The application of these results to privacy amplification shows that even very sparse channels can lead to significant privacy amplification when used as a post-processing step after local differentially private mechanisms.
title Bounds on the privacy amplification of arbitrary channels via the contraction of $f_α$-divergence
topic Information Theory
url https://arxiv.org/abs/2501.11473