Structack: Structure-based Adversarial Attacks on Graph Neural Networks

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


Recent work has shown that graph neural networks (GNNs) are vulnerable to adversarial attacks on graph data. Common attack approaches are typically informed, i.e.They have access to information about node attributes such as labels and feature vectors. In this work, we study adversarial attacks that are uninformed, where an attacker only has access to the graph structure, but no information about node attributes. Here the attacker aims to exploit structural knowledge and assumptions, which GNN models make about graph data. In particular, literature has shown that structural node centrality and similarity have a strong influence on learning with GNNs. Therefore, we study the impact of centrality and similarity on adversarial attacks on GNNs. We demonstrate that attackers can exploit this information to decrease the performance of GNNs by focusing on injecting links between nodes of low similarity and, surprisingly, low centrality. We show that structure-based uninformed attacks can approach the performance of informed attacks, while being computationally more efficient. With our paper, we present a new attack strategy on GNNs that we refer to as Structack. Structack can successfully manipulate the performance of GNNs with very limited information while operating under tight computational constraints. Our work contributes towards building more robust machine learning approaches on graphs.

Original languageEnglish
Title of host publicationHT 2021 - Proceedings of the 32nd ACM Conference on Hypertext and Social Media
PublisherAssociation of Computing Machinery
Number of pages10
ISBN (Electronic)9781450385510
Publication statusPublished - 30 Aug 2021
Event32nd ACM Conference on Hypertext and Social Media: HT 2021 - Virtuell, Ireland
Duration: 30 Aug 20212 Sept 2021


Conference32nd ACM Conference on Hypertext and Social Media
Abbreviated titleHT 2021


  • adversarial attacks
  • graph neural networks
  • network centrality
  • network similarity

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software


Dive into the research topics of 'Structack: Structure-based Adversarial Attacks on Graph Neural Networks'. Together they form a unique fingerprint.

Cite this