A recent study (Rice et al., 2020) revealed overfitting to be a dominant phenomenon in
adversarially robust training of deep networks, and that appropriate early-stopping of …

Deep neural networks (DNNs) are vulnerable to adversarial noises, which motivates the
benchmark of model robustness. Existing benchmarks mainly focus on evaluating defenses …

With the widespread applications of Deep Neural Networks (DNNs), the safety of DNNs has
become a significant issue. The vulnerability of the neural networks against adversarial …

Recently, several adversarial training methods have been proposed for rejecting
perturbation-based adversarial examples, which enhance the robustness of deep neural …

Adversarial examples pose a significant challenge to the security of deep neural networks
(DNNs). In order to defend against malicious attacks, adversarial training forces DNNs to …

Label Smoothing (LS) is a widely-used training technique that adjusts hard labels towards a
softer distribution, which prevents model being over-confidence and enhances model …

Deep learning (DL) methodology contributes a lot to the development of hyperspectral
image (HSI) analysis community. However, it also makes HSI analysis systems vulnerable to …

Purpose Deep learning has achieved impressive performance across a variety of tasks,
including medical image processing. However, recent research has shown that deep neural …

Adversarial training methods commonly generate initial perturbations that are independent
across epochs, and obtain subsequent adversarial training samples without selection …

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial
attacks, where the predictions of a model can be drastically altered by slight modifications to …