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

Deep neural networks (DNNs) are vulnerable to adversarial attacks. Inparticular, object detectors may be attacked by applying a particularadversarial patch to the image. However, because the patch shrinks duringpreprocessing, most existing approaches that employ adversarial patches toattack object detectors would diminish the attack success rate on small andmedium targets. This paper proposes a Frequency Module(FRAN), afrequency-domain attention module for guiding patch generation. This is thefirst study to introduce frequency domain attention to optimize the attackcapabilities of adversarial patches. Our method increases the attack successrates of small and medium targets by 4.18% and 3.89%, respectively, over thestate-of-the-art attack method for fooling the human detector while assaultingYOLOv3 without reducing the attack success rate of big targets.

Using Frequency Attention to Make Adversarial Patch Powerful Against Person Detector