Robust network alignment via attack signal scaling and adversarial perturbation elimination

Yang Zhou, Zeru Zhang, Sixing Wu, Victor Sheng, Xiaoying Han, Zijie Zhang, Ruoming Jin

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

14 Scopus citations

Abstract

Recent studies have shown that graph learning models are highly vulnerable to adversarial attacks, and network alignment methods are no exception. How to enhance the robustness of network alignment against adversarial attacks remains an open research problem. In this paper, we propose a robust network alignment solution, RNA, for offering preemptive protection of existing network alignment algorithms, enhanced with the guidance of effective adversarial attacks. First, we analyze how popular iterative gradient-based adversarial attack techniques suffer from gradient vanishing issues and show a fake sense of attack effectiveness. Based on dynamical isometry theory, an attack signal scaling (ASS) method with established upper bound of feasible signal scaling is introduced to alleviate the gradient vanishing issues for effective adversarial attacks while maintaining the decision boundary of network alignment. Second, we develop an adversarial perturbation elimination (APE) model to neutralize adversarial nodes in vulnerable space to adversarial-free nodes in safe area, by integrating Dirac delta approximation (DDA) techniques and the LSTM models. Our proposed APE method is able to provide proactive protection to existing network alignment algorithms against adversarial attacks. The theoretical analysis demonstrates the existence of an optimal distribution for the APE model to reach a lower bound. Last but not least, extensive evaluation on real datasets presents that RNA is able to offer the preemptive protection to trained network alignment methods against three popular adversarial attack models.

Original languageEnglish
Title of host publicationThe Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021
PublisherAssociation for Computing Machinery, Inc
Pages3884-3895
Number of pages12
ISBN (Electronic)9781450383127
DOIs
StatePublished - Apr 19 2021
Event2021 World Wide Web Conference, WWW 2021 - Ljubljana, Slovenia
Duration: Apr 19 2021Apr 23 2021

Publication series

NameThe Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021

Conference

Conference2021 World Wide Web Conference, WWW 2021
Country/TerritorySlovenia
CityLjubljana
Period04/19/2104/23/21

Keywords

  • Adversarial Perturbation Elimination
  • Network Alignment

Fingerprint

Dive into the research topics of 'Robust network alignment via attack signal scaling and adversarial perturbation elimination'. Together they form a unique fingerprint.

Cite this