Adversarial Examples on Graph Data: Deep Insights into Attack and Defense

By Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu. 2019

514 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/26a0e0d17910c6676fcfa1cebe0cb7f5cd17080c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Lichao Sun
2. Marinka Zitnik
3. Yingtong Dou
4. Philip S. Yu
5. Yao Ma
6. Tyler Derr
7. Jiliang Tang
8. Wei Jin

Citations in the corpus

• Graph Information Bottleneck (2020, unknown): “es or structure [15,16]. Accordingly, several defense models are proposed to increase the robustness by injecting random noise in the representations [33], removing suspicious and uninformative edges [34], low-rank approximation of the adjacency matrix [35], additional hinge loss for certified robust”
• Graph Structure Learning for Robust Graph Neural Networks (2020, background): “ks based on meta-learning. Although increasing efforts have been devoted to developing adversarial attacks on graph data, the research about improving the robustness of GNNs has just started recently [28, 32, 38, 41]. One way to solve the problem is to learn a robust network by penalizing the attent”
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks (2020, methodology): “Recent studies [31, 17] found that most damaging attacks add fake edges between nodes that have different features and labels.”
• Graph Neural Networks for Graphs With Heterophily: A Survey (2022, unknown): “While early studies focused on homophilic graphs [119], [120], recent work recognizes structural attacks inherently exhibit heterophily (Fig.”
• Adversarial Attack and Defense on Graph Data: A Survey (2018, methodology): “Attack Model GNN [8], [12], [17], [21], [23], [28], [73], [92], [93], [103], [106], [125], [145], [147] [20], [36], [42], [49], [67], [96], [97], [104], [120], [122], [134], [141], [146] Non-GNN [2], [18], [19], [24], [27], [33], [43], [50], [108], [109], [128], [129], [136], [143] [26], [34], [39] ”
• Node Similarity Preserving Graph Convolutional Networks (2020, methodology): “GCN-Jaccard [34] and Pro-GNN [14] implemented by DeepRobust [21],”