A survey of adversarial learning on graphs
Deep learning models on graphs have achieved remarkable performance in various graph
analysis tasks, eg, node classification, link prediction, and graph clustering. However, they …
analysis tasks, eg, node classification, link prediction, and graph clustering. However, they …
Adversarial attack and defense on graph data: A survey
Deep neural networks (DNNs) have been widely applied to various applications, including
image classification, text generation, audio recognition, and graph data analysis. However …
image classification, text generation, audio recognition, and graph data analysis. However …
State of the art on adversarial attacks and defenses in graphs
Z Zhai, P Li, S Feng - Neural Computing and Applications, 2023 - Springer
Graph neural networks (GNNs) had shown excellent performance in complex graph data
modelings such as node classification, link prediction and graph classification. However …
modelings such as node classification, link prediction and graph classification. However …
Certifiable robustness to graph perturbations
Despite the exploding interest in graph neural networks there has been little effort to verify
and improve their robustness. This is even more alarming given recent findings showing that …
and improve their robustness. This is even more alarming given recent findings showing that …
Expressive 1-lipschitz neural networks for robust multiple graph learning against adversarial attacks
Recent findings have shown multiple graph learning models, such as graph classification
and graph matching, are highly vulnerable to adversarial attacks, ie small input …
and graph matching, are highly vulnerable to adversarial attacks, ie small input …
V-infor: A robust graph neural networks explainer for structurally corrupted graphs
GNN explanation method aims to identify an explanatory subgraph which contains the most
informative components of the full graph. However, a major limitation of existing GNN …
informative components of the full graph. However, a major limitation of existing GNN …
Integrated defense for resilient graph matching
A recent study has shown that graph matching models are vulnerable to adversarial
manipulation of their input which is intended to cause a mismatching. Nevertheless, there is …
manipulation of their input which is intended to cause a mismatching. Nevertheless, there is …
Robust network alignment via attack signal scaling and adversarial perturbation elimination
Recent studies have shown that graph learning models are highly vulnerable to adversarial
attacks, and network alignment methods are no exception. How to enhance the robustness …
attacks, and network alignment methods are no exception. How to enhance the robustness …
Robust meta network embedding against adversarial attacks
Recent studies have shown that graph mining models are vulnerable to adversarial attacks.
This paper proposes a robust meta network embedding framework, RoMNE, which improves …
This paper proposes a robust meta network embedding framework, RoMNE, which improves …
Adversarial analysis of similarity-based sign prediction
Adversarial social network analysis explores how social links can be altered or otherwise
manipulated to hinder unwanted information collection. To date, however, problems of this …
manipulated to hinder unwanted information collection. To date, however, problems of this …