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 algorithms have achieved state-of-the-art performance for Image
Classification. For this reason, they have been used even in security-critical applications …

The intriguing phenomenon of adversarial examples has attracted significant attention in
machine learning and what might be more surprising to the community is the existence of …

Existing neural network-based autonomous systems are shown to be vulnerable against
adversarial attacks, therefore sophisticated evaluation of their robustness is of great …

Universal adversarial perturbation (UAP), ie a single perturbation to fool the network for most
images, is widely recognized as a more practical attack because the UAP can be generated …

Deep neural networks (DNNs) have achieved remarkable success in various tasks (eg,
image classification, speech recognition, and natural language processing (NLP)). However …

Post-hoc gradient-based interpretability methods [Simonyan et al., 2013, Smilkov et al.,
2017] that provide instance-specific explanations of model predictions are often based on …

Adversarial examples, generated by carefully crafted perturbation, have attracted
considerable attention in research fields. Recent works have argued that the existence of the …

Deep learning models (with neural networks) have been widely used in challenging tasks
such as computer-aided disease diagnosis based on medical images. Recent studies have …

The booming interest in adversarial attacks stems from a misalignment between human
vision and a deep neural network (DNN),\ie~ a human imperceptible perturbation fools the …