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 neural networks are susceptible to small-but-specific adversarialperturbations capable of deceiving the network. This vulnerability can lead topotentially harmful consequences in security-critical applications. To addressthis vulnerability, we propose a novel metric called \emph{Gradient Similarity}that allows us to capture the influence of training data on test inputs. Weshow that \emph{Gradient Similarity} behaves differently for normal andadversarial inputs, and enables us to detect a variety of adversarial attackswith a near perfect ROC-AUC of 95-100\%. Even white-box adversaries equippedwith perfect knowledge of the system cannot bypass our detector easily. On theMNIST dataset, white-box attacks are either detected with a high ROC-AUC of87-96\%, or require very high distortion to bypass our detector.

Gradient Similarity: An Explainable Approach to Detect Adversarial Attacks against Deep Learning