Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

The popularity of adapting deep neural networks (DNNs) in solving hard problems has
increased substantially. Specifically, in the field of computer vision, DNNs are becoming a …

Deep neural network-based image classifications are vulnerable to adversarial
perturbations. The image classifications can be easily fooled by adding artificial small and …

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 …

Recent studies have demonstrated that existing deep neural networks (DNNs) on 3D point
clouds are vulnerable to adversarial examples, especially under the white-box settings …

The tremendous amount of accessible data in cyberspace face the risk of being
unauthorized used for training deep learning models. To address this concern, methods are …

Decision-based attack poses a severe threat to real-world applications since it regards the
target model as a black box and only accesses the hard prediction label. Great efforts have …

Deep neural networks (DNNs) are vulnerable to adversarial examples with small
perturbations. Adversarial defense thus has been an important means which improves the …

Deep neural networks have shown great potential in many practical applications, yet their
knowledge is at the risk of being stolen via exposed services (\eg APIs). In contrast to the …

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 …