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

We improve the robustness of Deep Neural Net (DNN) to adversarial attacks byusing an interpolating function as the output activation. This data-dependentactivation remarkably improves both the generalization and robustness of DNN.In the CIFAR10 benchmark, we raise the robust accuracy of the adversariallytrained ResNet20 from $\sim 46\%$ to $\sim 69\%$ under the state-of-the-artIterative Fast Gradient Sign Method (IFGSM) based adversarial attack. When wecombine this data-dependent activation with total variation minimization onadversarial images and training data augmentation, we achieve an improvement inrobust accuracy by 38.9$\%$ for ResNet56 under the strongest IFGSM attack.Furthermore, We provide an intuitive explanation of our defense by analyzingthe geometry of the feature space.

Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization