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

Recent works have developed several methods of defending neural networksagainst adversarial attacks with certified guarantees. However, thesetechniques can be computationally costly due to the use of certification duringtraining. We develop a new regularizer that is both more efficient thanexisting certified defenses, requiring only one additional forward propagationthrough a network, and can be used to train networks with similar certifiedaccuracy. Through experiments on MNIST and CIFAR-10 we demonstrate improvementsin training speed and comparable certified accuracy compared tostate-of-the-art certified defenses.

Fast Training of Provably Robust Neural Networks by SingleProp