Link Membership Inference Attacks against Unsupervised Graph Representation Learning

Xiuling Wang, Wendy Hui Wang

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

1 Scopus citations

Abstract

Significant advancements have been made in recent years in the field of unsupervised graph representation learning (UGRL) approaches. UGRL involves representing large graphs as low-dimensional vectors, commonly referred to as embeddings. These embeddings can be publicly released or shared with third parties for downstream analytics. However, adversaries can deduce sensitive structural information from the target graph through its embedding using various types of privacy inference attacks. This paper investigates the privacy vulnerabilities of UGRL models through the lens of link membership inference attack (LMIA). Specifically, an LMIA adversary aims to infer whether any two nodes are connected in the target graph from the node embeddings generated by a UGRL model. To achieve this, we propose two LMIA attacks that leverage the properties of node embeddings and various forms of adversary knowledge for inference. By conducting experiments on four state-of-the-art UGRL models using five real-world graph datasets, we demonstrate the effectiveness of the two LMIA attacks against these UGRL models. Furthermore, we conduct a comprehensive analysis to examine how varying degrees of preserved structural information in the embeddings impact the performance of LMIA. To enhance the security of UGRL models against LMIA, we design a family of defense mechanisms that perturb the least significant dimensions of embeddings. Our experimental results show that our defense mechanism achieves a favorable balance between defense effectiveness and embedding quality.

Original languageEnglish
Title of host publicationProceedings - 39th Annual Computer Security Applications Conference, ACSAC 2023
Pages477-491
Number of pages15
ISBN (Electronic)9798400708862
DOIs
StatePublished - 4 Dec 2023
Event39th Annual Computer Security Applications Conference, ACSAC 2023 - Austin, United States
Duration: 4 Dec 20238 Dec 2023

Publication series

NameACM International Conference Proceeding Series

Conference

Conference39th Annual Computer Security Applications Conference, ACSAC 2023
Country/TerritoryUnited States
CityAustin
Period4/12/238/12/23

Keywords

  • graph learning
  • machine learning privacy
  • membership inference attack
  • trustworthy machine learning.
  • Unsupervised graph representation learning

Fingerprint

Dive into the research topics of 'Link Membership Inference Attacks against Unsupervised Graph Representation Learning'. Together they form a unique fingerprint.

Cite this