De2GNN reduces degree bias in adversarial defenses by removing heterophilic links, adding homophilic links to tail nodes, and fusing a kNN feature view through node-wise attention, improving tail-node accuracy under Metattack.
Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks. As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability. Adversary can mislead GNNs to give wrong predictions by modifying the graph structure such as manipulating a few edges. This vulnerability has arisen tremendous concerns for adapting GNNs in safety-critical applications and has attracted increasing research attention in recent years. Thus, it is necessary and timely to provide a comprehensive overview of existing graph adversarial attacks and the countermeasures. In this survey, we categorize existing attacks and defenses, and review the corresponding state-of-the-art methods. Furthermore, we have developed a repository with representative algorithms (https://github.com/DSE-MSU/DeepRobust/tree/master/deeprobust/graph). The repository enables us to conduct empirical studies to deepen our understandings on attacks and defenses on graphs.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mitigating the Structural Bias in Graph Adversarial Defenses
De2GNN reduces degree bias in adversarial defenses by removing heterophilic links, adding homophilic links to tail nodes, and fusing a kNN feature view through node-wise attention, improving tail-node accuracy under Metattack.