Current methods for training robust networks lead to a drop in test accuracy, which has led
prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning …

To improve the robustness of deep classifiers against adversarial perturbations, many
approaches have been proposed, such as designing new architectures with better …

We study the average robustness notion in deep neural networks in (selected) wide and
narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in …

Recent years have witnessed the success of deep convolutional neural networks for image
classification and many related tasks. It should be pointed out that the existing training …

Designing neural networks with bounded Lipschitz constant is a promising way to obtain
certifiably robust classifiers against adversarial examples. However, the relevant progress …

This paper introduces a new parameterization of deep neural networks (both fully-connected
and convolutional) with guaranteed $\ell^ 2$ Lipschitz bounds, ie limited sensitivity to input …

Deep neural networks for computer vision are deployed in increasingly safety-critical and
socially-impactful applications, motivating the need to close the gap in model performance …

Deep neural networks have recently shown impressive classification performance on a
diverse set of visual tasks. When deployed in real-world (noise-prone) environments, it is …

It is a highly desirable property for deep networks to be robust against small input changes.
One popular way to achieve this property is by designing networks with a small Lipschitz …

It is well-known that modern neural networks are vulnerable to adversarial examples. To
mitigate this problem, a series of robust learning algorithms have been proposed. However …