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

Deep learning models are being integrated into a wide range of high-impact,security-critical systems, from self-driving cars to medical diagnosis.However, recent research has demonstrated that many of these deep learningarchitectures are vulnerable to adversarial attacks--highlighting the vitalneed for defensive techniques to detect and mitigate these attacks before theyoccur. To combat these adversarial attacks, we developed UnMask, an adversarialdetection and defense framework based on robust feature alignment. The coreidea behind UnMask is to protect these models by verifying that an image'spredicted class ("bird") contains the expected robust features (e.g., beak,wings, eyes). For example, if an image is classified as "bird", but theextracted features are wheel, saddle and frame, the model may be under attack.UnMask detects such attacks and defends the model by rectifying themisclassification, re-classifying the image based on its robust features. Ourextensive evaluation shows that UnMask (1) detects up to 96.75% of attacks, and(2) defends the model by correctly classifying up to 93% of adversarial imagesproduced by the current strongest attack, Projected Gradient Descent, in thegray-box setting. UnMask provides significantly better protection thanadversarial training across 8 attack vectors, averaging 31.18% higher accuracy.We open source the code repository and data with this paper:https://github.com/safreita1/unmask.

UnMask: Adversarial Detection and Defense Through Robust Feature Alignment