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 propose a defence strategy to improve adversarialrobustness by incorporating hidden layer representation. The key of thisdefence strategy aims to compress or filter input information includingadversarial perturbation. And this defence strategy can be regarded as anactivation function which can be applied to any kind of neural network. We alsoprove theoretically the effectiveness of this defense strategy under certainconditions. Besides, incorporating hidden layer representation we propose threetypes of adversarial attacks to generate three types of adversarial examples,respectively. The experiments show that our defence method can significantlyimprove the adversarial robustness of deep neural networks which achieves thestate-of-the-art performance even though we do not adopt adversarial training.

Incorporating Hidden Layer representation into Adversarial Attacks and Defences