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

Model robustness against adversarial examples of single perturbation typesuch as the $\ell_{p}$-norm has been widely studied, yet its generalization tomore realistic scenarios involving multiple semantic perturbations and theircomposition remains largely unexplored. In this paper, we first propose a novelmethod for generating composite adversarial examples. Our method can find theoptimal attack composition by utilizing component-wise projected gradientdescent and automatic attack-order scheduling. We then propose generalizedadversarial training (GAT) to extend model robustness from $\ell_{p}$-ball tocomposite semantic perturbations, such as the combination of Hue, Saturation,Brightness, Contrast, and Rotation. Results obtained using ImageNet andCIFAR-10 datasets indicate that GAT can be robust not only to all the testedtypes of a single attack, but also to any combination of such attacks. GAT alsooutperforms baseline $\ell_{\infty}$-norm bounded adversarial trainingapproaches by a significant margin.

Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations