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 this paper, we explore the robustness of the Multi-Task Deep NeuralNetworks (MT-DNN) against non-targeted adversarial attacks across NaturalLanguage Understanding (NLU) tasks as well as some possible ways to defendagainst them. Liu et al., have shown that the Multi-Task Deep Neural Network,due to the regularization effect produced when training as a result of itscross task data, is more robust than a vanilla BERT model trained only on onetask (1.1%-1.5% absolute difference). We further show that although the MT-DNNhas generalized better, making it easily transferable across domains and tasks,it can still be compromised as after only 2 attacks (1-character and2-character) the accuracy drops by 42.05% and 32.24% for the SNLI and SciTailtasks. Finally, we propose a domain agnostic defense which restores the model'saccuracy (36.75% and 25.94% respectively) as opposed to a general-purposedefense or an off-the-shelf spell checker.

Exploring and Improving Robustness of Multi Task Deep Neural Networks via Domain Agnostic Defenses