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

While great progress has been made at making neural networks effective acrossa wide range of visual tasks, most models are surprisingly vulnerable. Thisfrailness takes the form of small, carefully chosen perturbations of theirinput, known as adversarial examples, which represent a security threat forlearned vision models in the wild -- a threat which should be responsiblydefended against in safety-critical applications of computer vision. In thispaper, we advocate for and experimentally investigate the use of a family oflogit regularization techniques as an adversarial defense, which can be used inconjunction with other methods for creating adversarial robustness at little tono marginal cost. We also demonstrate that much of the effectiveness of onerecent adversarial defense mechanism can in fact be attributed to logitregularization, and show how to improve its defense against both white-box andblack-box attacks, in the process creating a stronger black-box attack againstPGD-based models. We validate our methods on three datasets and include resultson both gradient-free attacks and strong gradient-based iterative attacks withas many as 1,000 steps.

Improved Adversarial Robustness via Logit Regularization Methods