Attack Graph Convolutional Networks by Adding Fake Nodes

In this paper, we study the robustness of graph convolutional networks (GCNs). Previous work have shown that GCNs are vulnerable to adversarial perturbation on adjacency or feature matrices of existing nodes; however, such attacks are usually unrealistic in real applications. For instance, in social...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-09
Hauptverfasser:	Wang, Xiaoyun, Cheng, Minhao, Eaton, Joe, Cho-Jui Hsieh, Wu, Felix
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Classification Cybersecurity Greedy algorithms Nodes Perturbation Social networks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!