Can I read A Unified Wasserstein Distributional Robustness Framework for Adversarial Training on EtoBox?

A Unified Wasserstein Distributional Robustness Framework for Adversarial Training by Bui, Tuan Anh; Le, Trung; Tran, Quan; Zhao, He; Phung, Dinh is a scholarly article available to read on EtoBox.

What is A Unified Wasserstein Distributional Robustness Framework for Adversarial Training about?

It is well-known that deep neural networks (DNNs) are susceptible to adversarial attacks, exposing a severe fragility of deep learning systems. As the result, adversarial training (AT) method, by incorporating adversarial examples during training, represents a natural and effective approach to strengthen the robustness of a DNN-based classifier. However, most AT-based methods, notably PGD-AT and TRADES, typically seek a pointwise adversary that generates the worst-case adversarial example by independently perturbing each data sample, as a way to "probe" the vulnerability of the classifier. Arguably, there are unexplored benefits in considering such adversarial effects from an entire distribution. To this end, this paper presents a unified framework that connects Wasserstein distributional robustness with current state-of-the-art AT methods. We introduce a new Wasserstein cost function and a new series of risk functions, with which we show that standard AT methods are special cases of their counterparts in our framework. This connection leads to an intuitive relaxation and generalization of existing AT methods and facilitates the development of a new family of distributional robustn

Author

Bui, Tuan Anh; Le, Trung; Tran, Quan; Zhao, He; Phung, Dinh

Published

2022

Language

EN