Although current deep learning techniques have yielded superior performance on various
computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial …

For a standard convolutional neural network, optimizing over the input pixels to maximize
the score of some target class will generally produce a grainy-looking version of the original …

Adversarial training is a powerful type of defense against adversarial examples. Previous
empirical results suggest that adversarial training requires wider networks for better …

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 …

Neural network robustness has recently been highlighted by the existence of adversarial
examples. Many previous works show that the learned networks do not perform well on …

The vulnerability of deep neural networks to adversarial samples has been a major
impediment to their broad applications, despite their success in various fields. Recently …

Important insights towards the explainability of neural networks reside in the characteristics
of their decision boundaries. In this work, we borrow tools from the field of adversarial …

Robust overfitting widely exists in adversarial training of deep networks. The exact
underlying reasons for this are still not completely understood. Here, we explore the causes …

Adversarial robustness has emerged as an important topic in deep learning as carefully
crafted attack samples can significantly disturb the performance of a model. Many recent …

Abstract Recent advances in Deep Learning show the existence of image-agnostic quasi-
imperceptible perturbations that when applied toany'image can fool a state-of-the-art …