Structack: Structure-based Adversarial Attacks on Graph Neural Networks

ACM Conference on Hypertext and Social Media (HT), pp. 111–120

Abstract

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.

Authors 6

1. Hussain Hussain

   Graz University of Technology · Know Center Research GmbH (Austria)

   Affiliation as printed

   Graz University of Technology & Know Center GmbH, Graz, Austria

2. Tomislav Đuričić

   Graz University of Technology · Know Center Research GmbH (Austria)

   Affiliation as printed

   Graz University of Technology & Know Center GmbH, Graz, Austria

3. Elisabeth Lex

   Graz University of Technology

   Affiliation as printed

   Graz University of Technology, Graz, Austria

4. Denis Helić

   Graz University of Technology

   Affiliation as printed

   Graz University of Technology, Graz, Austria

5. Markus Strohmaier Aachen

   GESIS - Leibniz Institute for the Social Sciences · RWTH Aachen University

   Affiliation as printed

   RWTH Aachen & GESIS - Leibniz Institute for the Social Sciences, Aachen, Germany

6. Roman Kern

   Graz University of Technology · Know Center Research GmbH (Austria)

   Affiliation as printed

   Graz University of Technology & Know Center GmbH, Graz, Austria