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

Convolutional neural network-based medical image classifiers have been shownto be especially susceptible to adversarial examples. Such instabilities arelikely to be unacceptable in the future of automated diagnoses. Thoughstatistical adversarial example detection methods have proven to be effectivedefense mechanisms, additional research is necessary that investigates thefundamental vulnerabilities of deep-learning-based systems and how best tobuild models that jointly maximize traditional and robust accuracy. This paperpresents the inclusion of attention mechanisms in CNN-based medical imageclassifiers as a reliable and effective strategy for increasing robust accuracywithout sacrifice. This method is able to increase robust accuracy by up to 16%in typical adversarial scenarios and up to 2700% in extreme cases.

Adversarially Robust Medical Classification via Attentive Convolutional Neural Networks