Correctly classifying adversarial examples is an essential but challenging requirement for
safely deploying machine learning models. As reported in RobustBench, even the state-of …

Recently, there is an emerging interest in adversarially training a classifier with a rejection
option (also known as a selective classifier) for boosting adversarial robustness. While …

Adversarial training (AT) is one of the most effective strategies for promoting model
robustness, whereas even the state-of-the-art adversarially trained models struggle to …

Building reliable AI decision support systems requires a robust set of data on which to train
models; both with respect to quantity and diversity. Obtaining such datasets can be difficult in …

Robustness towards adversarial attacks is a vital property for classifiers in several
applications such as autonomous driving, medical diagnosis, etc. Also, in such scenarios …

Both transduction and rejection have emerged as important techniques for defending
against adversarial perturbations. A recent work by Tram\er showed that, in the rejection …

Both transduction and rejection have emerged as important techniques for defending
against adversarial perturbations. A recent work by Goldwasser et. al showed that rejection …

Deep learning has achieved remarkable success in various domains, including computer
vision, natural language processing, and game playing. However, this success relies on the …

Both transduction and rejection have emerged as key techniques to enable stronger
defenses against adversarial perturbations, but existing work has not investigated the …