Adversarial training is one of the most effective approaches defending against adversarial
examples for deep learning models. Unlike other defense strategies, adversarial training …

In the past few years, it has become increasingly evident that deep neural networks are not
resilient enough to withstand adversarial perturbations in input data, leaving them …

We introduce a set of image transformations that can be used as corruptions to evaluate the
robustness of models as well as data augmentation mechanisms for training neural …

Several works have proposed Simplicity Bias (SB)---the tendency of standard training
procedures such as Stochastic Gradient Descent (SGD) to find simple models---to justify why …

Recent research finds CNN models for image classification demonstrate overlapped
adversarial vulnerabilities: adversarial attacks can mislead CNN models with small …

Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign
method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms …

Neural networks trained with SGD were recently shown to rely preferentially on linearly-
predictive features and can ignore complex, equally-predictive ones. This simplicity bias can …

While the transferability property of adversarial examples allows the adversary to perform
black-box attacks ie, the attacker has no knowledge about the target model), the transfer …

In recent years, researches on adversarial attacks and defense mechanisms have obtained
much attention. It's observed that adversarial examples crafted with small malicious …

Deep neural networks (DNNs) have achieved remarkable success in various tasks (eg,
image classification, speech recognition, and natural language processing (NLP)). However …