Saved in:
Bibliographic Details
Main Authors: Hehir, Jonathan, Niu, Xiaoyue, Slavkovic, Aleksandra
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.12520
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909582208532480
author Hehir, Jonathan
Niu, Xiaoyue
Slavkovic, Aleksandra
author_facet Hehir, Jonathan
Niu, Xiaoyue
Slavkovic, Aleksandra
contents How do we interpret the differential privacy (DP) guarantee for network data? We take a deep dive into a popular form of network DP ($\varepsilon$--edge DP) to find that many of its common interpretations are flawed. Drawing on prior work for privacy with correlated data, we interpret DP through the lens of adversarial hypothesis testing and demonstrate a gap between the pairs of hypotheses actually protected under DP (tests of complete networks) and the sorts of hypotheses implied to be protected by common claims (tests of individual edges). We demonstrate some conditions under which this gap can be bridged, while leaving some questions open. While some discussion is specific to edge DP, we offer selected results in terms of abstract DP definitions and provide discussion of the implications for other forms of network DP.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12520
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpreting Network Differential Privacy
Hehir, Jonathan
Niu, Xiaoyue
Slavkovic, Aleksandra
Statistics Theory
Computers and Society
How do we interpret the differential privacy (DP) guarantee for network data? We take a deep dive into a popular form of network DP ($\varepsilon$--edge DP) to find that many of its common interpretations are flawed. Drawing on prior work for privacy with correlated data, we interpret DP through the lens of adversarial hypothesis testing and demonstrate a gap between the pairs of hypotheses actually protected under DP (tests of complete networks) and the sorts of hypotheses implied to be protected by common claims (tests of individual edges). We demonstrate some conditions under which this gap can be bridged, while leaving some questions open. While some discussion is specific to edge DP, we offer selected results in terms of abstract DP definitions and provide discussion of the implications for other forms of network DP.
title Interpreting Network Differential Privacy
topic Statistics Theory
Computers and Society
url https://arxiv.org/abs/2504.12520