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

We present a method for adversarial attack detection based on the inspectionof a sparse set of neurons. We follow the hypothesis that adversarial attacksintroduce imperceptible perturbations in the input and that these perturbationschange the state of neurons relevant for the concepts modelled by the attackedmodel. Therefore, monitoring the status of these neurons would enable thedetection of adversarial attacks. Focusing on the image classification task,our method identifies neurons that are relevant for the classes predicted bythe model. A deeper qualitative inspection of these sparse set of neuronsindicates that their state changes in the presence of adversarial samples.Moreover, quantitative results from our empirical evaluation indicate that ourmethod is capable of recognizing adversarial samples, produced bystate-of-the-art attack methods, with comparable accuracy to that ofstate-of-the-art detectors.

Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?