English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we investigate on improving the adversarial robustnessobtained in adversarial training (AT) via reducing the difficulty ofoptimization. To better study this problem, we build a novel Bregman divergenceperspective for AT, in which AT can be viewed as the sliding process of thetraining data points on the negative entropy curve. Based on this perspective,we analyze the learning objectives of two typical AT methods, i.e., PGD-AT andTRADES, and we find that the optimization process of TRADES is easier thanPGD-AT for that TRADES separates PGD-AT. In addition, we discuss the functionof entropy in TRADES, and we find that models with high entropy can be betterrobustness learners. Inspired by the above findings, we propose two methods,i.e., FAIT and MER, which can both not only reduce the difficulty ofoptimization under the 10-step PGD adversaries, but also provide betterrobustness. Our work suggests that reducing the difficulty of optimizationunder the 10-step PGD adversaries is a promising approach for enhancing theadversarial robustness in AT.

Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training