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

Raw deep neural network (DNN) performance is not enough; in real-worldsettings, computational load, training efficiency and adversarial security arejust as or even more important. We propose to simultaneously tacklePerformance, Efficiency, and Robustness, using our proposed algorithm Q-TART,Quickly Train for Adversarial Robustness and in-Transferability. Q-TART followsthe intuition that samples highly susceptible to noise strongly affect thedecision boundaries learned by DNNs, which in turn degrades their performanceand adversarial susceptibility. By identifying and removing such samples, wedemonstrate improved performance and adversarial robustness while using only asubset of the training data. Through our experiments we highlight Q-TART's highperformance across multiple Dataset-DNN combinations, including ImageNet, andprovide insights into the complementary behavior of Q-TART alongside existingadversarial training approaches to increase robustness by over 1.3% while usingup to 17.9% less training time.

Q-TART: Quickly Training for Adversarial Robustness and in-Transferability