Deep learning as performed by artificial deep neural networks (DNNs) has achieved great
successes recently in many important areas that deal with text, images, videos, graphs, and …

Graph neural networks (GNNs) which apply the deep neural networks to graph data have
achieved significant performance for the task of semi-supervised node classification …

It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-
called physical adversarial examples deceive DNN-based decision makers by attaching …

Powerful adversarial attack methods are vital for understanding how to construct robust
deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper …

By adding human-imperceptible noise to clean images, the resultant adversarial examples
can fool other unknown models. Features of a pixel extracted by deep neural networks …

It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks,
which are implemented by adding crafted perturbations onto benign examples. Min-max …

Deep neural networks are susceptible to adversarial attacks due to the accumulation of
perturbations in the feature level, and numerous works have boosted model robustness by …

Although attention mechanisms have been widely used in deep learning for many tasks,
they are rarely utilized to solve multiple instance learning (MIL) problems, where only a …

Deep neural networks (DNNs) are vulnerable to adversarial examples where inputs with
imperceptible perturbations mislead DNNs to incorrect results. Despite the potential risk they …

Recent works have empirically shown that there exist adversarial examples that can be
hidden from neural network interpretability (namely, making network interpretation maps …