Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

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 …

Deep learning technology is increasingly being applied in safety-critical scenarios but has
recently been found to be susceptible to imperceptible adversarial perturbations. This raises …

Deep neural networks, particularly face recognition models, have been shown to be
vulnerable to both digital and physical adversarial examples. However, existing adversarial …

Robustness against word substitutions has a well-defined and widely acceptable form, ie,
using semantically similar words as substitutions, and thus it is considered as a fundamental …

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 …

Adversarial examples are inputs with imperceptible perturbations that easily misleading
deep neural networks (DNNs). Recently, adversarial patch, with noise confined to a small …

Facially manipulated images and videos or DeepFakes can be used maliciously to fuel
misinformation or defame individuals. Therefore, detecting DeepFakes is crucial to increase …

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 …