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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper proposes a black-box adversarial attack method to automatic speechrecognition systems. Some studies have attempted to attack neural networks forspeech recognition; however, these methods did not consider the robustness ofgenerated adversarial examples against timing lag with a target speech. Theproposed method in this paper adopts Evolutionary Multi-objective Optimization(EMO)that allows it generating robust adversarial examples under black-boxscenario. Experimental results showed that the proposed method successfullygenerated adjust-free adversarial examples, which are sufficiently robustagainst timing lag so that an attacker does not need to take the timing ofplaying it against the target speech.

Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition