Deep learning technology is increasingly being applied in safety-critical scenarios but has
recently been found to be susceptible to imperceptible adversarial perturbations. This raises …

Robust overfitting widely exists in adversarial training of deep networks. The exact
underlying reasons for this are still not completely understood. Here, we explore the causes …

Abstract Knowledge distillation is a simple yet effective technique for deep model
compression, which aims to transfer the knowledge learned by a large teacher model to a …

Knowledge discovery of heterogeneous data is an active topic in knowledge engineering.
Feature selection for heterogeneous data is an important part of effective data analysis …

Despite their success, vision transformers still remain vulnerable to image corruptions, such
as noise or blur. Indeed, we find that the vulnerability mainly stems from the unstable self …

Abstract Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial
examples. Adversarial training (AT) is a popular and effective strategy to defend against …

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 …

Modern deep neural networks have made numerous breakthroughs in real-world
applications, yet they remain vulnerable to some imperceptible adversarial perturbations …

Adversarial training (AT) is the most commonly used mechanism to improve the robustness
of deep neural networks. Recently, a novel adversarial attack against intermediate layers …

Overfitting widely exists in adversarial robust training of deep networks. An effective remedy
is adversarial weight perturbation, which injects the worst-case weight perturbation during …