Structack: Structure-based Adversarial Attacks on Graph Neural Networks

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.

[1]  Kilian Q. Weinberger,et al.  Simplifying Graph Convolutional Networks , 2019, ICML.

[2]  Lise Getoor,et al.  Query-driven Active Surveying for Collective Classification , 2012 .

[3]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[4]  Xiao-Ming Wu,et al.  Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning , 2018, AAAI.

[5]  Peter J. Bickel,et al.  Community Detection in Networks using Graph Distance , 2014, ArXiv.

[6]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[7]  Suhang Wang,et al.  Attacking Graph Convolutional Networks via Rewiring , 2019, ArXiv.

[8]  M. Newman.  Mathematics of networks , 2018, Oxford Scholarship Online.

[9]  Wenwu Zhu,et al.  Robust Graph Convolutional Networks Against Adversarial Attacks , 2019, KDD.

[10]  Le Song,et al.  Adversarial Attack on Graph Structured Data , 2018, ICML.

[11]  Suhang Wang,et al.  Adversarial Attacks on Graph Neural Networks via Node Injections: A Hierarchical Reinforcement Learning Approach , 2020, WWW.

[12]  Jiliang Tang,et al.  Adversarial Attacks and Defenses on Graphs: A Review and Empirical Study , 2020, ArXiv.

[13]  U. Brandes.  A faster algorithm for betweenness centrality , 2001 .

[14]  Sadegh Aliakbary,et al.  Quantification and comparison of degree distributions in complex networks , 2013, 7'th International Symposium on Telecommunications (IST'2014).

[15]  Stephan Günnemann,et al.  Pitfalls of Graph Neural Network Evaluation , 2018, ArXiv.

[16]  Andrew McCallum,et al.  Automating the Construction of Internet Portals with Machine Learning , 2000, Information Retrieval.

[17]  Jean-Loup Guillaume,et al.  Fast unfolding of communities in large networks , 2008, 0803.0476.

[18]  Stephan Günnemann,et al.  Adversarial Attacks on Neural Networks for Graph Data , 2018, KDD.

[19]  Lise Getoor,et al.  Collective Classification in Network Data , 2008, AI Mag..

[20]  Qiaozhu Mei,et al.  Black-Box Adversarial Attacks on Graph Neural Networks with Limited Node Access , 2020, ArXiv.

[21]  Yixin Chen,et al.  Link Prediction Based on Graph Neural Networks , 2018, NeurIPS.

[22]  L. Freeman.  Centrality in social networks conceptual clarification , 1978 .

[23]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[24]  Talal Rahwan,et al.  Hiding individuals and communities in a social network , 2016, Nature Human Behaviour.

[25]  Stephan Gunnemann,et al.  Adversarial Attacks on Graph Neural Networks via Meta Learning , 2019, ICLR.

[26]  Liming Zhu,et al.  Adversarial Examples on Graph Data: Deep Insights into Attack and Defense , 2019 .

[27]  Sijia Liu,et al.  Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective , 2019, IJCAI.

[28]  Lada A. Adamic,et al.  The political blogosphere and the 2004 U.S. election: divided they blog , 2005, LinkKDD '05.

[29]  Suhang Wang,et al.  Graph Structure Learning for Robust Graph Neural Networks , 2020, KDD.

[30]  Denis Helic,et al.  On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks , 2020, COMPLEX NETWORKS.