Graph neural networks (GNNs) have made rapid developments in the recent years. Due to
their great ability in modeling graph-structured data, GNNs are vastly used in various …

A machine learning model is traditionally considered robust if its prediction remains (almost)
constant under input perturbations with small norm. However, real-world tasks like molecular …

Real-world data is complex and often consists of objects that can be decomposed into
multiple entities (eg images into pixels, graphs into interconnected nodes). Randomized …

Deep Graph Learning (DGL) has emerged as a crucial technique across various domains.
However, recent studies have exposed vulnerabilities in DGL models, such as susceptibility …

Despite the success of graph neural networks (GNNs), their vulnerability to adversarial
attacks poses tremendous challenges for practical applications. Existing defense methods …

Graph neural networks (GNNs) are vulnerable to adversarial perturbations, especially for
topology attacks, and many methods that improve the robustness of GNNs have received …

Adversarial training (AT) refers to integrating adversarial examples--inputs altered with
imperceptible perturbations that can significantly impact model predictions--into the training …

We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that
are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In …

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

Remote sensing image classification is pivotal in applications ranging from environmental
monitoring to urban planning. However, the scarcity of labeled data in target domains often …