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 robustness is a research area that has recently received a lot ofattention in the quest for trustworthy artificial intelligence. However, recentworks on adversarial robustness have focused on supervised learning where it isassumed that labeled data is plentiful. In this paper, we investigatesemi-supervised adversarial training where labeled data is scarce. We derivetwo upper bounds for the robust risk and propose a regularization term forunlabeled data motivated by these two upper bounds. Then, we develop asemi-supervised adversarial training algorithm that combines the proposedregularization term with knowledge distillation using a semi-supervised teacher(i.e., a teacher model trained using a semi-supervised learning algorithm). Ourexperiments show that our proposed algorithm achieves state-of-the-artperformance with significant margins compared to existing algorithms. Inparticular, compared to supervised learning algorithms, performance of ourproposed algorithm is not much worse even when the amount of labeled data isvery small. For example, our algorithm with only 8\% labeled data is comparableto supervised adversarial training algorithms that use all labeled data, bothin terms of standard and robust accuracies on CIFAR-10.

Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation