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

With the development of high computational devices, deep neural networks(DNNs), in recent years, have gained significant popularity in many ArtificialIntelligence (AI) applications. However, previous efforts have shown that DNNswere vulnerable to strategically modified samples, named adversarial examples.These samples are generated with some imperceptible perturbations but can foolthe DNNs to give false predictions. Inspired by the popularity of generatingadversarial examples for image DNNs, research efforts on attacking DNNs fortextual applications emerges in recent years. However, existing perturbationmethods for images cannotbe directly applied to texts as text data is discrete.In this article, we review research works that address this difference andgeneratetextual adversarial examples on DNNs. We collect, select, summarize,discuss and analyze these works in a comprehensive way andcover all the relatedinformation to make the article self-contained. Finally, drawing on thereviewed literature, we provide further discussions and suggestions on thistopic.

Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey