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

Machine learning models have been successfully applied to a wide range ofapplications including computer vision, natural language processing, and speechrecognition. A successful implementation of these models however, usuallyrelies on deep neural networks (DNNs) which are treated as opaque black-boxsystems due to their incomprehensible complexity and intricate internalmechanism. In this work, we present a novel algorithm for explaining thepredictions of a DNN using adversarial machine learning. Our approachidentifies the relative importance of input features in relation to thepredictions based on the behavior of an adversarial attack on the DNN. Ouralgorithm has the advantage of being fast, consistent, and easy to implementand interpret. We present our detailed analysis that demonstrates how thebehavior of an adversarial attack, given a DNN and a task, stays consistent forany input test data point proving the generality of our approach. Our analysisenables us to produce consistent and efficient explanations. We illustrate theeffectiveness of our approach by conducting experiments using a variety ofDNNs, tasks, and datasets. Finally, we compare our work with other well-knowntechniques in the current literature.

An Adversarial Approach for Explaining the Predictions of Deep Neural Networks