Can Directed Graph Neural Networks be Adversarially Robust?

TL;DR

This paper investigates the adversarial robustness of directed graph neural networks, introduces a new attack setting and a universal defense framework, significantly improving robustness and accuracy.

Contribution

It is the first to study GNN robustness on directed graphs and proposes a novel, efficient message-passing framework to enhance their adversarial resilience.

Findings

Existing directed GNNs are not adversarially robust.

The proposed framework significantly improves robustness against transfer and adaptive attacks.

Achieves state-of-the-art performance with high clean accuracy.

Abstract

The existing research on robust Graph Neural Networks (GNNs) fails to acknowledge the significance of directed graphs in providing rich information about networks' inherent structure. This work presents the first investigation into the robustness of GNNs in the context of directed graphs, aiming to harness the profound trust implications offered by directed graphs to bolster the robustness and resilience of GNNs. Our study reveals that existing directed GNNs are not adversarially robust. In pursuit of our goal, we introduce a new and realistic directed graph attack setting and propose an innovative, universal, and efficient message-passing framework as a plug-in layer to significantly enhance the robustness of GNNs. Combined with existing defense strategies, this framework achieves outstanding clean accuracy and state-of-the-art robust performance, offering superior defense against both transfer and adaptive attacks. The findings in this study reveal a novel and promising direction for this crucial research area. The code will be made publicly available upon the acceptance of this work.