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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent studies have found that deep learning systems are vulnerable toadversarial examples; e.g., visually unrecognizable adversarial images caneasily be crafted to result in misclassification. The robustness of neuralnetworks has been studied extensively in the context of adversary detection,which compares a metric that exhibits strong discriminate power between naturaland adversarial examples. In this paper, we propose to characterize theadversarial subspaces through the lens of mutual information (MI) approximatedby conditional generation methods. We use MI as an information-theoretic metricto strengthen existing defenses and improve the performance of adversarydetection. Experimental results on MagNet defense demonstrate that our proposedMI detector can strengthen its robustness against powerful adversarial attacks.

On The Utility of Conditional Generation Based Mutual Information for Characterizing Adversarial Subspaces