Benefiting from the rapid development of deep learning, 2D and 3D computer vision
applications are deployed in many safe-critical systems, such as autopilot and identity …

Deep neural networks have achieved unprecedented success on diverse vision tasks.
However, they are vulnerable to adversarial noise that is imperceptible to humans. This …

Vision transformers (ViTs) have been successfully deployed in a variety of computer vision
tasks, but they are still vulnerable to adversarial samples. Transfer-based attacks use a local …

A hard challenge in developing practical face recognition (FR) attacks is due to the black-
box nature of the target FR model, ie, inaccessible gradient and parameter information to …

While the transferability property of adversarial examples allows the adversary to perform
black-box attacks ie, the attacker has no knowledge about the target model), the transfer …

The emergence of Deep Neural Networks (DNNs) has revolutionized various domains,
enabling the resolution of complex tasks spanning image recognition, natural language …

Crowd counting, which has been widely adopted for estimating the number of people in
safety-critical scenes, is shown to be vulnerable to adversarial examples in the physical …

Though deep neural networks (DNNs) have revealed their extraordinary performance in the
fields of computer vision, it is evident that the vulnerability of DNNs to adversarial attacks …

The exponential growth of social media platforms such as Twitter and Facebook has
revolutionized textual communication and textual content publication in human society …

Adversarial detection aims to determine whether a given sample is an adversarial one
based on the discrepancy between natural and adversarial distributions. Unfortunately …