Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …

Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …

In recent years, researches on adversarial attacks and defense mechanisms have obtained
much attention. It's observed that adversarial examples crafted with small malicious …

Learning to reject is a special kind of self-awareness (the ability to know what you do not
know), which is an essential factor for humans to become smarter. Although machine …

Deep neural networks have demonstrated excellent performance in most computer vision
tasks in recent years. However, they are vulnerable to adversarial perturbations generated …

With the rapid advancements and notable achievements across various application
domains, Machine Learning (ML) has become a vital element within the Internet of Things …

Recent studies have shown that robustness to adversarial attacks can be transferred across
deep neural networks. In other words, we can make a weak model more robust with the help …

Classic results establish that encouraging predictive diversity improves performance in
ensembles of low-capacity models, eg through bagging or boosting. Here we demonstrate …

Ensemble of networks with bidirectional knowledge distillation does not significantly improve
on the performance of ensemble of networks without bidirectional knowledge distillation. We …

Despite the fundamental distinction between adversarial and natural training (AT and NT),
AT methods generally adopt momentum SGD (MSGD) for the outer optimization. This paper …