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

Existing pixel-level adversarial attacks on neural networks may be deficientin real scenarios, since pixel-level changes on the data cannot be fullydelivered to the neural network after camera capture and multiple imagepreprocessing steps. In contrast, in this paper, we argue from anotherperspective that gaussian blurring, a common technique of image preprocessing,can be aggressive itself in specific occasions, thus exposing the network toreal-world adversarial attacks. We first propose an adversarial attack demonamed peak suppression (PS) by suppressing the values of peak elements in thefeatures of the data. Based on the blurring spirit of PS, we further applygaussian blurring to the data, to investigate the potential influence andthreats of gaussian blurring to performance of the network. Experiment resultsshow that PS and well-designed gaussian blurring can form adversarial attacksthat completely change classification results of a well-trained target network.With the strong physical significance and wide applications of gaussianblurring, the proposed approach will also be capable of conducting real worldattacks.

Blurring Fools the Network -- Adversarial Attacks by Feature Peak Suppression and Gaussian Blurring