NotAllLow-PassFiltersareRobust inGraphConvolutionalNetworks

Graph Convolutional Networks (GCNs) elaborate the expressive power of deep learning from grid-like data to graph-structured data and have achieved remarkable success in a wide variety of domains [7, 6, 13, 27, 22, 30, 1, 8, 42, 18, 31, 12, 41, 19]. Just like CNNs, modern GCNs could promisingly learn both the local and global structural patterns of graphs through designed convolutions. However, the vulnerability of GCNs against adversarial attacks has been revealed recently [70, 11, 9]. The lack of robustness arouses concerns on applying GCNs in a variety of fields pertaining to security and privacy.