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 …

Open-world classification systems should discern out-of-distribution (OOD) data whose
labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD …

Robust generalization aims to tackle the most challenging data distributions which are rare
in the training set and contain severe noises, ie, photon-limited corruptions. Common …

Abstract Out-of-distribution (OOD) detection aims to identify OOD data based on
representations extracted from well-trained deep models. However, existing methods largely …

Machine learning models are vulnerable to Out-Of-Distribution (OOD) examples, and such a
problem has drawn much attention. However, current methods lack a full understanding of …

Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by
slightly perturbing the features of correctly labeled training examples. By formalizing this …

Although current deep learning techniques have yielded superior performance on various
computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial …

To improve the robustness of deep classifiers against adversarial perturbations, many
approaches have been proposed, such as designing new architectures with better …

The robustness of a deep classifier can be characterized by its margins: the decision
boundary's distances to natural data points. However, it is unclear whether existing robust …

Adversarial phenomenon has been widely observed in machine learning (ML) systems,
especially in those using deep neural networks, describing that ML systems may produce …