Computer vision using deep neural networks (DNNs) has brought about seminal changes in
people's lives. Applications range from automotive, face recognition in the security industry …

Various transfer attack methods have been proposed to evaluate the robustness of deep
neural networks (DNNs). Although manifesting remarkable performance in generating …

Recently non-transferable learning (NTL) was proposed to restrict models' generalization
toward the target domain (s) which serves as state-of-the-art solutions for intellectual …

As an effective data augmentation method, Mixup synthesizes an extra amount of samples
through linear interpolations. Despite its theoretical dependency on data properties, Mixup …

Large earthquakes can be destructive and quickly wreak havoc on a landscape. To mitigate
immediate threats, early warning systems have been developed to alert residents …

Assessing the robustness of deep neural networks against out-of-distribution inputs is
crucial, especially in safety-critical domains like autonomous driving, but also in safety …

The performance of computer vision models are susceptible to unexpected changes in input
images, known as common corruptions (eg noise, blur, illumination changes, etc.), that can …

The performance of image classification on well-known benchmarks such as ImageNet is
remarkable, but in safety-critical situations, the accuracy often drops significantly under …