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

Adversarial examples are inputs to machine learning models designed by anadversary to cause an incorrect output. So far, adversarial examples have beenstudied most extensively in the image domain. In this domain, adversarialexamples can be constructed by imperceptibly modifying images to causemisclassification, and are practical in the physical world. In contrast,current targeted adversarial examples applied to speech recognition systemshave neither of these properties: humans can easily identify the adversarialperturbations, and they are not effective when played over-the-air. This papermakes advances on both of these fronts. First, we develop effectivelyimperceptible audio adversarial examples (verified through a human study) byleveraging the psychoacoustic principle of auditory masking, while retaining100% targeted success rate on arbitrary full-sentence targets. Next, we makeprogress towards physical-world over-the-air audio adversarial examples byconstructing perturbations which remain effective even after applying realisticsimulated environmental distortions.

Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition