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 …

We study the node classification problem on feature-decorated graphs in the sparse setting,
ie, when the expected degree of a node is $ O (1) $ in the number of nodes, in the fixed …

Graph Neural Networks (GNNs) have demonstrated state-of-the-art performance in various
graph representation learning tasks. Recently, studies revealed their vulnerability to …

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 …

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

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 …

Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing
neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues …

Contrastive learning (CL) has emerged as a powerful framework for learning
representations of images and text in a self-supervised manner while enhancing model …

Generalization of machine learning models can be severely compromised by data
poisoning, where adversarial changes are applied to the training data. This vulnerability has …

Current defenses against graph attacks often rely on certain properties to eliminate structural
perturbations by identifying adversarial edges from normal edges. However, this …