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

Neural networks are deployed widely in natural language processing tasks onthe industrial scale, and perhaps the most often they are used as compounds ofautomatic machine translation systems. In this work, we present a simpleapproach to fool state-of-the-art machine translation tools in the task oftranslation from Russian to English and vice versa. Using a novel black-boxgradient-free tensor-based optimizer, we show that many online translationtools, such as Google, DeepL, and Yandex, may both produce wrong or offensivetranslations for nonsensical adversarial input queries and refuse to translateseemingly benign input phrases. This vulnerability may interfere withunderstanding a new language and simply worsen the user's experience whileusing machine translation systems, and, hence, additional improvements of thesetools are required to establish better translation.

Translate your gibberish: black-box adversarial attack on machine translation systems