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

Neural networks are vulnerable to adversarial examples, which poses a threatto their application in security sensitive systems. We propose high-levelrepresentation guided denoiser (HGD) as a defense for image classification.Standard denoiser suffers from the error amplification effect, in which smallresidual adversarial noise is progressively amplified and leads to wrongclassifications. HGD overcomes this problem by using a loss function defined asthe difference between the target model's outputs activated by the clean imageand denoised image. Compared with ensemble adversarial training which is thestate-of-the-art defending method on large images, HGD has three advantages.First, with HGD as a defense, the target model is more robust to eitherwhite-box or black-box adversarial attacks. Second, HGD can be trained on asmall subset of the images and generalizes well to other images and unseenclasses. Third, HGD can be transferred to defend models other than the oneguiding it. In NIPS competition on defense against adversarial attacks, our HGDsolution won the first place and outperformed other models by a large margin.

Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser