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

Black-box attacks usually face two problems: poor transferability and theinability to evade the adversarial defense. To overcome these shortcomings, wecreate an original approach to generate adversarial examples by smoothing thelinear structure of the texture in the benign image, called AdvSmo. Weconstruct the adversarial examples without relying on any internal informationto the target model and design the imperceptible-high attack success rateconstraint to guide the Gabor filter to select appropriate angles and scales tosmooth the linear texture from the input images to generate adversarialexamples. Benefiting from the above design concept, AdvSmo will generateadversarial examples with strong transferability and solid evasiveness.Finally, compared to the four advanced black-box adversarial attack methods,for the eight target models, the results show that AdvSmo improves the averageattack success rate by 9% on the CIFAR-10 and 16% on the Tiny-ImageNet datasetcompared to the best of these attack methods.

AdvSmo: Black-box Adversarial Attack by Smoothing Linear Structure of Texture