Abstract Despite their performance, Artificial Neural Networks are not reliable enough for
most of industrial applications. They are sensitive to noises, rotations, blurs and adversarial …

Over the last few years, the phenomenon of adversarial examples---maliciously constructed
inputs that fool trained machine learning models---has captured the attention of the research …

Adversarial Robustness is a growing field that evidences the brittleness of neural networks.
Although the literature on adversarial robustness is vast, a dimension is missing in these …

Neural Networks have been shown to be sensitive to common perturbations such as blur,
Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious …

In this paper we establish rigorous benchmarks for image classifier robustness. Our first
benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while …

Adversarial images are designed to mislead deep neural networks (DNNs), attracting great
attention in recent years. Although several defense strategies achieved encouraging …

Deep learning solutions are vulnerable to adversarial perturbations and can lead a" frog"
image to be misclassified as a" deer" or random pattern into" guitar". Adversarial attack …

In practice, deep neural networks have been found to be vulnerable to various types of
noise, such as adversarial examples and corruption. Various adversarial defense methods …

Abstract Though Deep Neural Networks (DNN) show excellent performance across various
computer vision tasks, several works show their vulnerability to adversarial samples, ie …

While neural networks have achieved high accuracy on standard image classification
benchmarks, their accuracy drops to nearly zero in the presence of small adversarial …