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

In recent years, deep neural networks demonstrated state-of-the-artperformance in a large variety of tasks and therefore have been adopted in manyapplications. On the other hand, the latest studies revealed that neuralnetworks are vulnerable to adversarial examples obtained by carefully addingsmall perturbation to legitimate samples. Based upon the observation, manyattack methods were proposed. Among them, the optimization-based CW attack isthe most powerful as the produced adversarial samples present much lessdistortion compared to other methods. The better attacking effect, however,comes at the cost of running more iterations and thus longer computation timeto reach desirable results. In this work, we propose to leverage theinformation of gradients as a guidance during the search of adversaries. Morespecifically, directly incorporating the gradients into the perturbation can beregarded as a constraint added to the optimization process. We intuitively andempirically prove the rationality of our method in reducing the search space.Our experiments show that compared to the original CW attack, the proposedmethod requires fewer iterations towards adversarial samples, obtaining ahigher success rate and resulting in smaller $\ell_2$ distortion.

Towards Leveraging the Information of Gradients in Optimization-based Adversarial Attack