Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those
that affect both node features and graph topology. This paper investigates GNNs derived …

Despite its success in the image domain, adversarial training did not (yet) stand out as an
effective defense for Graph Neural Networks (GNNs) against graph structure perturbations …

Node injection attacks on Graph Neural Networks (GNNs) have received increasing
attention recently, due to their ability to degrade GNN performance with high attack success …

Existing knowledge graph (KG) models for commonsense question answering present two
challenges:(i) existing methods retrieve entities related to questions from the knowledge …

Deep graph learning (DGL) has achieved remarkable progress in both business and
scientific areas ranging from finance and e-commerce to drug and advanced material …

Purpose Denial-of-service (DoS) attacks develop unauthorized entry to various network
services and user information by building traffic that creates multiple requests …

Abstract Graph Neural Networks (GNNs) have shown remarkable achievements and have
been extensively applied in various downstream tasks, such as node classification and …

Abstract Graph Neural Networks (GNNs) demonstrate powerful capabilities in graph
representation learning tasks. However, real-world graphs are often perturbed and come …

Abstract Graph Neural Networks (GNNs) have been widely used in multiple fields, but they
exhibit vulnerable performance when faced with adversarial attacks. Therefore, researching …

Graph Neural Networks (GNNs) have demonstrated significant application potential in
various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous …