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

The increasing importance of both deep neural networks (DNNs) and cloudservices for training them means that bad actors have more incentive andopportunity to insert backdoors to alter the behavior of trained models. Inthis paper, we introduce a novel method for backdoor detection that extractsfeatures from pre-trained DNN's weights using independent vector analysis (IVA)followed by a machine learning classifier. In comparison to other detectiontechniques, this has a number of benefits, such as not requiring any trainingdata, being applicable across domains, operating with a wide range of networkarchitectures, not assuming the nature of the triggers used to change networkbehavior, and being highly scalable. We discuss the detection pipeline, andthen demonstrate the results on two computer vision datasets regarding imageclassification and object detection. Our method outperforms the competingalgorithms in terms of efficiency and is more accurate, helping to ensure thesafe application of deep learning and AI.

Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks