Although deep networks achieve strong accuracy on a range of computer vision
benchmarks, they remain vulnerable to adversarial attacks, where imperceptible input …

Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep
neural networks. Since then, extensive efforts have been devoted to enhancing the …

Despite their unmatched performance, deep neural networks remain susceptible to targeted
attacks by nearly imperceptible levels of adversarial noise. While the underlying cause of …

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are
vulnerable to adversarial attacks, limiting their applications in security-critical systems …

Adversarial training has been demonstrated to be one of the most effective remedies for
defending adversarial examples, yet it often suffers from the huge robustness generalization …

Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks. A range of
defense methods have been proposed to train adversarially robust DNNs, among which …

Abstract Deep Neural Networks (DNNs) have achieved state-of-the-art performance in
various applications. It is crucial to verify that the high accuracy prediction for a given task is …

Skip connections are an essential component of current state-of-the-art deep neural
networks (DNNs) such as ResNet, WideResNet, DenseNet, and ResNeXt. Despite their …

Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial
examples---perturbed inputs specifically designed to produce intentional errors in the …

We propose Instruct2Attack (I2A), a language-guided semantic attack that generates
semantically meaningful perturbations according to free-form language instructions. We …