Neural networks are known to be vulnerable to adversarial examples. In this note, we
evaluate the two white-box defenses that appeared at CVPR 2018 and find they are …

Recent work has shown deep neural networks (DNNs) to be highly susceptible to well-
designed, small perturbations at the input layer, or so-called adversarial examples. Taking …

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 attacks on deep neural networks (DNNs) have been found for several years.
However, the existing adversarial attacks have high success rates only when the information …

Adversarial robustness has attracted much attention recently, and the mainstream solution is
adversarial training. However, the tradition of generating adversarial perturbations for each …

Several recent papers have discussed utilizing Lipschitz constants to limit the susceptibility
of neural networks to adversarial examples. We analyze recently proposed methods for …

Textual adversarial samples play important roles in multiple subfields of NLP research,
including security, evaluation, explainability, and data augmentation. However, most work …

The emergence of Deep Neural Networks (DNNs) has revolutionized various domains,
enabling the resolution of complex tasks spanning image recognition, natural language …

We study the behavior of several black-box search algorithms used for generating
adversarial examples for natural language processing (NLP) tasks. We perform a fine …

We attempt to interpret how adversarially trained convolutional neural networks (AT-CNNs)
recognize objects. We design systematic approaches to interpret AT-CNNs in both …