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

End-to-end semantic communication (ESC) system is able to improvecommunication efficiency by only transmitting the semantics of the input ratherthan raw bits. Although promising, ESC has also been shown susceptible to thecrafted physical layer adversarial perturbations due to the openness ofwireless channels and the sensitivity of neural models. Previous works focusmore on the physical layer white-box attacks, while the challenging black-boxones, as more practical adversaries in real-world cases, are still largelyunder-explored. To this end, we present SemBLK, a novel method that can learnto generate destructive physical layer semantic attacks for an ESC system underthe black-box setting, where the adversaries are imperceptible to humans.Specifically, 1) we first introduce a surrogate semantic encoder and train itsparameters by exploring a limited number of queries to an existing ESC system.2) Equipped with such a surrogate encoder, we then propose a novel semanticperturbation generation method to learn to boost the physical layer attackswith semantic adversaries. Experiments on two public datasets show theeffectiveness of our proposed SemBLK in attacking the ESC system under theblack-box setting. Finally, we provide case studies to visually justify thesuperiority of our physical layer semantic perturbations.

Boosting Physical Layer Black-Box Attacks with Semantic Adversaries in Semantic Communications