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 …

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …

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 …

Adversarial examples are commonly viewed as a threat to ConvNets. Here we present an
opposite perspective: adversarial examples can be used to improve image recognition …

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by
imperceptible perturbations. A range of defense techniques have been proposed to improve …

Adversarial examples have attracted significant attention in machine learning, but the
reasons for their existence and pervasiveness remain unclear. We demonstrate that …

The open-world deployment of Machine Learning (ML) algorithms in safety-critical
applications such as autonomous vehicles needs to address a variety of ML vulnerabilities …

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 …

Abstract We introduce Interpolation Consistency Training (ICT), a simple and computation
efficient algorithm for training Deep Neural Networks in the semi-supervised learning …

Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of
defense methods have been proposed to train adversarially robust DNNs, among which …