On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation

Zhanke Zhou, Chenyu Zhou, Xuan Li, Jiangchao Yao*, Quanming Yao, Bo Han*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

3 Citations (Scopus)

Abstract

Although powerful graph neural networks (GNNs) have boosted numerous real-world applications, the potential privacy risk is still underexplored. To close this gap, we perform the first comprehensive study of graph reconstruction attack that aims to reconstruct the adjacency of nodes. We show that a range of factors in GNNs can lead to the surprising leakage of private links. Especially by taking GNNs as a Markov chain and attacking GNNs via a flexible chain approximation, we systematically explore the underneath principles of graph reconstruction attack, and propose two information theory-guided mechanisms: (1) the chain-based attack method with adaptive designs for extracting more private information; (2) the chain-based defense method that sharply reduces the attack fidelity with moderate accuracy loss. Such two objectives disclose a critical belief that to recover better in attack, you must extract more multi-aspect knowledge from the trained GNN; while to learn safer for defense, you must forget more link-sensitive information in training GNNs. Empirically, we achieve state-of-the-art results on six datasets and three common GNNs. The code is publicly available at: https://github.com/tmlr-group/MC-GRA.
Original languageEnglish
Title of host publicationProceedings of the 40th International Conference on Machine Learning, ICML 2023
EditorsAndreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett
PublisherML Research Press
Pages42843-42877
Number of pages35
Volume202
Publication statusPublished - Jul 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023
https://icml.cc/Conferences/2023
https://proceedings.mlr.press/v202/
https://openreview.net/group?id=ICML.cc/2023/Conference

Publication series

NameProceedings of Machine Learning Research
Volume202
ISSN (Print)2640-3498

Conference

Conference40th International Conference on Machine Learning, ICML 2023
Country/TerritoryUnited States
CityHonolulu
Period23/07/2329/07/23
Internet address

Scopus Subject Areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation'. Together they form a unique fingerprint.

Cite this