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

In the past few years, it has become increasingly evident that deep neuralnetworks are not resilient enough to withstand adversarial perturbations ininput data, leaving them vulnerable to attack. Various authors have proposedstrong adversarial attacks for computer vision and Natural Language Processing(NLP) tasks. As a response, many defense mechanisms have also been proposed toprevent these networks from failing. The significance of defending neuralnetworks against adversarial attacks lies in ensuring that the model'spredictions remain unchanged even if the input data is perturbed. Severalmethods for adversarial defense in NLP have been proposed, catering todifferent NLP tasks such as text classification, named entity recognition, andnatural language inference. Some of these methods not only defend neuralnetworks against adversarial attacks but also act as a regularization mechanismduring training, saving the model from overfitting. This survey aims to reviewthe various methods proposed for adversarial defenses in NLP over the past fewyears by introducing a novel taxonomy. The survey also highlights the fragilityof advanced deep neural networks in NLP and the challenges involved indefending them.

A Survey of Adversarial Defences and Robustness in NLP