Backdoor attacks are serious security threats to machine learning models where an
adversary can inject poisoned samples into the training set, causing a backdoored model …

Adversarial robustness of deep models is pivotal in ensuring safe deployment in real world
settings, but most modern defenses have narrow scope and expensive costs. In this paper …

This work presents a comprehensive exploration of Reverse Engineering of Deceptions
(RED) in the field of adversarial machine learning. It delves into the intricacies of machine …

Adversarial Training (AT) has been demonstrated as one of the most effective methods
against adversarial examples. While most existing works focus on AT with a single type of …

Significant advances have been made in recent years in improving the robustness of deep
neural networks, particularly under adversarial machine learning scenarios where the data …

Existing certified training methods can only train models to be robust against a certain
perturbation type (eg $ l_\infty $ or $ l_2 $). However, an $ l_\infty $ certifiably robust model …

As AI systems become more complex and widespread, they require significant
computational power, increasing energy consumption. Addressing this challenge is …

Numerous adversarial attack methods have been developed to generate imperceptible
image perturbations that can cause erroneous predictions of state-of-the-art machine …

Deep neural networks (DNNs) have been adopted in many application domains due to their
superior performance. However, their susceptibility under test-time adversarial perturbations …

Deep learning models have been proven to be severely affected by adversarial examples,
which limit the widespread deployment of deep learning models. Prior research largely …