Can Directed Graph Neural Networks be Adversarially Robust?
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 36 references that are in the map. First posted on arXiv 3 Jun 2023.
Builds on
19 of 36 references.
References · 19
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
- 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
- 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
- 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
- 2018Adversarial Attack on Graph Structured Datacited by 301
- 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
- 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
- 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
- 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
- 2021MagNet: A Neural Network for Directed Graphscited by 107
- 2021Robustness of Graph Neural Networks at Scalecited by 100
7 more
- 2020Directed Graph Convolutional Networkcited by 73
- 2021Elastic Graph Neural Networkscited by 67
- 2018Fast Gradient Attack on Network Embeddingcited by 65
- 2018MotifNet: a motif-based Graph Convolutional Network for directed graphscited by 64
- 2019Certifiable Robustness and Robust Training for Graph Convolutional Networkscited by 59
- 2019Spectral-based Graph Convolutional Network for Directed Graphscited by 38
- 2023Are Defenses for Graph Neural Networks Robust?cited by 38
Built on by
Citing papers per year: 2024: 1.
1 paper.