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 Detection (AED) is a crucial defense technique againstadversarial attacks and has drawn increasing attention from the NaturalLanguage Processing (NLP) community. Despite the surge of new AED methods, ourstudies show that existing methods heavily rely on a shortcut to achieve goodperformance. In other words, current search-based adversarial attacks in NLPstop once model predictions change, and thus most adversarial examplesgenerated by those attacks are located near model decision boundaries. Tosurpass this shortcut and fairly evaluate AED methods, we propose to test AEDmethods with \textbf{F}ar \textbf{B}oundary (\textbf{FB}) adversarial examples.Existing methods show worse than random guess performance under this scenario.To overcome this limitation, we propose a new technique, \textbf{ADDMU},\textbf{a}dversary \textbf{d}etection with \textbf{d}ata and \textbf{m}odel\textbf{u}ncertainty, which combines two types of uncertainty estimation forboth regular and FB adversarial example detection. Our new method outperformsprevious methods by 3.6 and 6.0 \emph{AUC} points under each scenario. Finally,our analysis shows that the two types of uncertainty provided by \textbf{ADDMU}can be leveraged to characterize adversarial examples and identify the onesthat contribute most to model's robustness in adversarial training.

ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation