Finding MNEMON: Reviving Memories of Node Embeddings

Yun Shen, Yufei Han, Zhikun Zhang, Min Chen, Ting Yu, Michael Backes, Yang Zhang, Gianluca Stringhini

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Citations (Scopus)

Abstract

Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks. Little attention has been paid to understand the privacy risks of integrating the output from graph embedding models (e.g., node embeddings) with complex downstream machine learning pipelines. In this paper, we fill this gap and propose a novel model-agnostic graph recovery attack that exploits the implicit graph structural information preserved in the embeddings of graph nodes. We show that an adversary can recover edges with decent accuracy by only gaining access to the node embedding matrix of the original graph without interactions with the node embedding models. We demonstrate the effectiveness and applicability of our graph recovery attack through extensive experiments.

Original languageEnglish
Title of host publicationCCS 2022 - Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security
PublisherAssociation for Computing Machinery
Pages2643-2657
Number of pages15
ISBN (Electronic)9781450394505
DOIs
Publication statusPublished - 7 Nov 2022
Event28th ACM SIGSAC Conference on Computer and Communications Security, CCS 2022 - Los Angeles, United States
Duration: 7 Nov 202211 Nov 2022

Publication series

NameProceedings of the ACM Conference on Computer and Communications Security
ISSN (Print)1543-7221

Conference

Conference28th ACM SIGSAC Conference on Computer and Communications Security, CCS 2022
Country/TerritoryUnited States
CityLos Angeles
Period7/11/2211/11/22

Keywords

  • graph embedding
  • machine learning security and privacy

Fingerprint

Dive into the research topics of 'Finding MNEMON: Reviving Memories of Node Embeddings'. Together they form a unique fingerprint.

Cite this