no code implementations • 25 Nov 2023 • Ruiqi Feng, Zhichao Hou, Tyler Derr, Xiaorui Liu
The adversarial robustness of Graph Neural Networks (GNNs) has been questioned due to the false sense of security uncovered by strong adaptive attacks despite the existence of numerous defenses.
no code implementations • 16 Jul 2023 • Wendi Yu, Zhichao Hou, Xiaorui Liu
Polynomial graph filters have been widely used as guiding principles in the design of Graph Neural Networks (GNNs).
no code implementations • 3 Jun 2023 • Zhichao Hou, Xitong Zhang, Wei Wang, Charu C. Aggarwal, Xiaorui Liu
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.