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

Adversarial training, which is to enhance robustness against adversarialattacks, has received much attention because it is easy to generatehuman-imperceptible perturbations of data to deceive a given deep neuralnetwork. In this paper, we propose a new adversarial training algorithm that istheoretically well motivated and empirically superior to other existingalgorithms. A novel feature of the proposed algorithm is to apply moreregularization to data vulnerable to adversarial attacks than other existingregularization algorithms do. Theoretically, we show that our algorithm can beunderstood as an algorithm of minimizing the regularized empirical riskmotivated from a newly derived upper bound of the robust risk. Numericalexperiments illustrate that our proposed algorithm improves the generalization(accuracy on examples) and robustness (accuracy on adversarial attacks)simultaneously to achieve the state-of-the-art performance.

Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples