A targeted universal attack on graph convolutional network by using fake nodes
J Dai, W Zhu, X Luo - Neural Processing Letters, 2022 - Springer
Graph-structured data exist in numerous applications in real life. As a state-of-the-art graph
neural network, the graph convolutional network (GCN) plays an important role in …
neural network, the graph convolutional network (GCN) plays an important role in …
A targeted universal attack on graph convolutional network
J Dai, W Zhu, X Luo - arXiv preprint arXiv:2011.14365, 2020 - arxiv.org
Graph-structured data exist in numerous applications in real life. As a state-of-the-art graph
neural network, the graph convolutional network (GCN) plays an important role in …
neural network, the graph convolutional network (GCN) plays an important role in …
Graph adversarial attack via rewiring
Graph Neural Networks (GNNs) have demonstrated their powerful capability in learning
representations for graph-structured data. Consequently, they have enhanced the …
representations for graph-structured data. Consequently, they have enhanced the …
Attack graph convolutional networks by adding fake nodes
In this paper, we study the robustness of graph convolutional networks (GCNs). Previous
work have shown that GCNs are vulnerable to adversarial perturbation on adjacency or …
work have shown that GCNs are vulnerable to adversarial perturbation on adjacency or …
[PDF][PDF] Latent adversarial training of graph convolution networks
Despite the recent success of graph convolution networks (GCNs) in modeling graph
structured data, its vulnerability to adversarial attacks have been revealed and attacks on …
structured data, its vulnerability to adversarial attacks have been revealed and attacks on …
Fake node attacks on graph convolutional networks
In this paper, we study the robustness of graph convolutional networks (GCNs). Previous
works have shown that GCNs are vulnerable to adversarial perturbation on adjacency or …
works have shown that GCNs are vulnerable to adversarial perturbation on adjacency or …
Defensevgae: Defending against adversarial attacks on graph data via a variational graph autoencoder
A Zhang, J Ma - International Conference on Intelligent Computing, 2024 - Springer
Graph neural networks (GNNs) achieve remarkable performances for the tasks on graph
data. However, recent studies uncover that they are extremely vulnerable to adversarial …
data. However, recent studies uncover that they are extremely vulnerable to adversarial …
Enhancing robustness of graph convolutional networks via dropping graph connections
Graph convolutional networks (GCNs) have emerged as one of the most popular neural
networks for a variety of tasks over graphs. Despite their remarkable learning and inference …
networks for a variety of tasks over graphs. Despite their remarkable learning and inference …
A Dual Robust Graph Neural Network Against Graph Adversarial Attacks
Q Tao, J Liao, E Zhang, L Li - Neural Networks, 2024 - Elsevier
Abstract Graph Neural Networks (GNNs) have gained widespread usage and achieved
remarkable success in various real-world applications. Nevertheless, recent studies reveal …
remarkable success in various real-world applications. Nevertheless, recent studies reveal …
Adversarial detection on graph structured data
Graph Neural Networks (GNNs) has achieved tremendous development on perceptual tasks
in recent years, such as node classification, graph classification, link prediction, etc …
in recent years, such as node classification, graph classification, link prediction, etc …