Abstract Context Machine Learning (ML) has been at the heart of many innovations over the
past years. However, including it in so-called “safety-critical” systems such as automotive or …

Adversarial training (AT) has become the de-facto standard to obtain models robust against
adversarial examples. However, AT exhibits severe robust overfitting: cross-entropy loss on …

Recent work has shown that deep learning models in NLP are highly sensitive to low-level
correlations between simple features and specific output labels, leading to overfitting and …

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

Adversarial attacks against deep networks can be defended against either by building
robust classifiers or, by creating classifiers that can\emph {detect} the presence of …

This work concerns the development of deep networks that are certifiably robust to
adversarial attacks. Joint robust classification-detection was recently introduced as a …

Recently, several adversarial training methods have been proposed for rejecting
perturbation-based adversarial examples, which enhance the robustness of deep neural …

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 …

The softmax cross-entropy loss function has been widely used to train deep models for
various tasks. In this work, we propose a Gaussian mixture (GM) loss function for deep …