Adversarial training is one of the most effective approaches defending against adversarial
examples for deep learning models. Unlike other defense strategies, adversarial training …

The outstanding performance of deep neural networks has promoted deep learning
applications in a broad set of domains. However, the potential risks caused by adversarial …

Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

Adversarial training (AT) is always formulated as a minimax problem, of which the
performance depends on the inner optimization that involves the generation of adversarial …

Adversarial training based on the minimax formulation is necessary for obtaining adversarial
robustness of trained models. However, it is conservative or even pessimistic so that it …

Improving the robustness of deep neural networks (DNNs) to adversarial examples is an
important yet challenging problem for secure deep learning. Across existing defense …

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

Adversarial training has been widely acknowledged as the most effective method to improve
the adversarial robustness against adversarial examples for Deep Neural Networks (DNNs) …

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 …

Today's world is highly network interconnected owing to the pervasiveness of small personal
devices (eg, smartphones) as well as large computing devices or services (eg, cloud …