Recently, it was found that many real-world examples without intentional modifications can
fool machine learning models, and such examples are called" natural adversarial …

Although state-of-the-art object detection methods have shown compelling performance,
models often are not robust to adversarial attacks and out-of-distribution data. We introduce …

We introduce two challenging datasets that reliably cause machine learning model
performance to substantially degrade. The datasets are collected with a simple adversarial …

Many recent studies have shown that deep neural models are vulnerable to adversarial
samples: images with imperceptible perturbations, for example, can fool image classifiers. In …

The vulnerabilities of deep neural networks against adversarial examples have become a
significant concern for deploying these models in sensitive domains. Devising a definitive …

Despite the recent advancements in deploying neural networks for image classification, it
has been found that adversarial examples are able to fool these models leading them to …

Although recent deep neural network algorithm has shown tremendous success in several
computer vision tasks, their vulnerability against minute adversarial perturbations has raised …

Most of existing adversarial examples attacking methods for object detection models aim at
generating subtle perturbation which is invisible to human vision. However, some …

Deep learning plays a critical role in the applications of artificial intelligence. The trend of
processing images or videos as input data and pursuing execution efficiency in practical …

Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many
applications, especially in computer vision. However, CNNs still suffer from a tendency to …