Current adversarial attack research reveals the vulnerability of learning-based classifiers
against carefully crafted perturbations. However, most existing attack methods have inherent …

Abstract Vision-Language Pre-training (VLP) models have achieved remarkable success in
practice, while easily being misled by adversarial attack. Though harmful, adversarial …

Billions of people are sharing their daily live images on social media everyday. However,
malicious collectors use deep face recognition systems to easily steal their biometric …

White box adversarial perturbations are generated via iterative optimization algorithms most
often by minimizing an adversarial loss on a ℓ p neighborhood of the original image, the so …

In recent years, deep learning has gained widespread application across diverse fields,
including image classification and machine translation. Nevertheless, the emergence of …

Adversarial patch attacks which can mislead deep learning models and the human eye in
both the digital and physical domains have led to a trust crisis. Traditional approaches to …

The proliferation of images captured from millions of cameras and the advancement of facial
recognition (FR) technology have made the abuse of FR a severe privacy threat. Existing …

Existing studies have shown that malicious and imperceptible adversarial samples may
significantly weaken the reliability and validity of deep learning systems. Since gradient …

Deep neural networks in the area of information security are facing a severe threat from
adversarial examples (AEs). Existing methods of AE generation use two optimization …

Abstract Deep Neural Networks (DNNs) are susceptible to attacks by adversarial examples,
which could cause serious consequences in safety-critical systems. Towards recent studies …