Defending Graph Convolutional Networks Against Adversarial Attacks

The interconnection of social, email, and media platforms enables adversaries to manipulate networked data and promote their malicious intents. This paper introduces graph neural network architectures that are robust to perturbed networked data. The novel network utilizes a randomization layer that performs link-dithering (LD) by adding or removing links with probabilities selected to boost robustness. The resultant link-dithered auxiliary graphs are leveraged by an adaptive (A)GCN that performs SSL. The proposed robust LD-AGCN achieves performance gains relative to GCNs under perturbed network data.