Can Directed Graph Neural Networks be Adversarially Robust?
This addresses the crucial problem of adversarial vulnerabilities in directed GNNs for network analysis applications, representing a novel direction rather than incremental work.
This paper tackles the problem of adversarial robustness in directed graph neural networks (GNNs), revealing that existing directed GNNs are not robust and proposing a new message-passing framework that achieves state-of-the-art robust performance when combined with existing defenses.
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.