Following unprecedented success on the natural language tasks, Transformers have been
successfully applied to several computer vision problems, achieving state-of-the-art results …

Graph contrastive learning (GCL) has emerged as a dominant technique for graph
representation learning which maximizes the mutual information between paired graph …

The study on improving the robustness of deep neural networks against adversarial
examples grows rapidly in recent years. Among them, adversarial training is the most …

Abstract Model-based deep learning has achieved astounding successes due in part to the
availability of large-scale real-world data. However, processing such massive amounts of …

Modern deep neural networks (DNNs) have achieved state-of-the-art performances but are
typically over-parameterized. The over-parameterization may result in undesirably large …

Adversarial training has been demonstrated to be one of the most effective remedies for
defending adversarial examples, yet it often suffers from the huge robustness generalization …

In adversarial machine learning, deep neural networks can fit the adversarial examples on
the training dataset but have poor generalization ability on the test set. This phenomenon is …

Deep learning models have a propensity for fitting the entire training set even with random
labels, which requires memorization of every training sample. In this paper, we explore the …

Adversarial training is widely used to improve the robustness of deep neural networks to
adversarial attack. However, adversarial training is prone to overfitting, and the cause is far …

Abstract Adversarial Robustness Distillation (ARD) aims to transfer the robustness of large
teacher models to small student models, facilitating the attainment of robust performance on …