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

One popular hypothesis of neural network generalization is that the flatlocal minima of loss surface in parameter space leads to good generalization.However, we demonstrate that loss surface in parameter space has no obviousrelationship with generalization, especially under adversarial settings.Through visualizing decision surfaces in both parameter space and input space,we instead show that the geometry property of decision surface in input spacecorrelates well with the adversarial robustness. We then propose an adversarialrobustness indicator, which can evaluate a neural network's intrinsicrobustness property without testing its accuracy under adversarial attacks.Guided by it, we further propose our robust training method. Without involvingadversarial training, our method could enhance network's intrinsic adversarialrobustness against various adversarial attacks.

Interpreting Adversarial Robustness: A View from Decision Surface in Input Space