It has been recognized that the data generated by the denoising diffusion probabilistic
model (DDPM) improves adversarial training. After two years of rapid development in …

Existing adversarial learning approaches mostly use class labels to generate adversarial
samples that lead to incorrect predictions, which are then used to augment the training of the …

Correctly classifying adversarial examples is an essential but challenging requirement for
safely deploying machine learning models. As reported in RobustBench, even the state-of …

With the rapid development of deep learning, training Big Models (BMs) for multiple
downstream tasks becomes a popular paradigm. Researchers have achieved various …

Objective: The hand function of individuals with spinal cord injury (SCI) plays a crucial role in
their independence and quality of life. Wearable cameras provide an opportunity to analyze …

Edge Federation is a new computing paradigm that seamlessly interconnects the resources
of multiple edge service providers. A key challenge in such systems is the deployment of …

Deep neural network (DNN)-based applications are extensively being researched and
applied in the Internet of Things (IoT) devices in daily lives due to impressive performance …

Adversarial training (AT) is one of the most effective strategies for promoting model
robustness, whereas even the state-of-the-art adversarially trained models struggle to …

Adversarial purification using generative models demonstrates strong adversarial defense
performance. These methods are classifier and attack-agnostic, making them versatile but …

Nowadays, there has been a strikingly remarkable success in computer vision, owing to the
boom of deep learning. Nevertheless, the revelation of adversarial examples has …