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

Image classification must work for autonomous vehicles (AV) operating onpublic roads, and actions performed based on image misclassification can haveserious consequences. Traffic sign images can be misclassified by anadversarial attack on machine learning models used by AVs for traffic signrecognition. To make classification models resilient against adversarialattacks, we used a hybrid deep-learning model with both the quantum andclassical layers. Our goal is to study the hybrid deep-learning architecturefor classical-quantum transfer learning models to support the current era ofintermediate-scale quantum technology. We have evaluated the impacts of variouswhite box adversarial attacks on these hybrid models. The classical part ofhybrid models includes a convolution network from the pre-trained Resnet18model, which extracts informative features from a high dimensional LISA trafficsign image dataset. The output from the classical processor is processedfurther through the quantum layer, which is composed of various quantum gatesand provides support to various quantum mechanical features like entanglementand superposition. We have tested multiple combinations of quantum circuits toprovide better classification accuracy with decreasing training data and foundbetter resiliency for our hybrid classical-quantum deep learning model duringattacks compared to the classical-only machine learning models.

Hybrid Classical-Quantum Deep Learning Models for Autonomous Vehicle Traffic Image Classification Under Adversarial Attack