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

Although deep neural networks have shown promising performances on varioustasks, they are susceptible to incorrect predictions induced by imperceptiblysmall perturbations in inputs. A large number of previous works proposed todetect adversarial attacks. Yet, most of them cannot effectively detect themagainst adaptive whitebox attacks where an adversary has the knowledge of themodel and the defense method. In this paper, we propose a new probabilisticadversarial detector motivated by a recently introduced non-robust feature. Weconsider the non-robust features as a common property of adversarial examples,and we deduce it is possible to find a cluster in representation spacecorresponding to the property. This idea leads us to probability estimatedistribution of adversarial representations in a separate cluster, and leveragethe distribution for a likelihood based adversarial detector.

Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection