Skip to main navigation Skip to search Skip to main content

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 contributionAcademicpeer-review

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
Subtitle of host publicationProceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security
PublisherACM
Pages2643-2657
Number of pages15
ISBN (Electronic)9781450394505
DOIs
Publication statusPublished - 2022

Publication series

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

Funding

We wish to thank the anonymous reviewers for their feedback and our shepherd Gergely Acs for his help in improving our paper. This work is partially funded by the Helmholtz Association within the project “Trustworthy Federated Data Analytics” (TFDA) (funding number ZT-I-OO1 4) and by the National Science Foundation under grant CNS-2127232.

FundersFunder number
Helmholtz Association
National Science Foundation2127232, CNS-2127232
TFDAZT-I-OO1 4

    Fingerprint

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

    Cite this