Adversarial training is considered one of the most effective methods to improve the
adversarial robustness of deep neural networks. Despite the success, it still suffers from …

Adversarial training is the most popular and general strategy to improve Deep Neural
Network (DNN) robustness against adversarial noises. Many adversarial training methods …

In today's era of social media, where information spreads rapidly through platforms like
YouTube, Facebook, and Twitter, the development of generative models have given rise to a …

Adversarial Training has proved to be an effective training paradigm to enforce robustness
against adversarial examples in modern neural network architectures. Despite many efforts …

Thermal imaging detection has been applied in many scenarios. However, its security has
not been fully explored. We propose a physical attack method with small bulbs on a board to …

In this paper, on the basis of in-depth research on the key technology of binocular vision
measurement; a set of multidimension online measurement system for image recognition is …

Deep neural networks (DNNs), especially convolutional neural networks (CNNs), have
achieved remarkable state-of-the-art performance in various applications [3]. However …

The widespread adoption of deep neural networks (DNNs) has raised significant concerns
about their robustness, particularly in real-world environments characterized by inherent …