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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep neural networks (DNNs) are well known to be vulnerable to adversarialexamples (AEs). In addition, AEs have adversarial transferability, which meansAEs generated for a source model can fool another black-box model (targetmodel) with a non-trivial probability. In previous studies, it was confirmedthat the vision transformer (ViT) is more robust against the property ofadversarial transferability than convolutional neural network (CNN) models suchas ConvMixer, and moreover encrypted ViT is more robust than ViT without anyencryption. In this article, we propose a random ensemble of encrypted ViTmodels to achieve much more robust models. In experiments, the proposed schemeis verified to be more robust against not only black-box attacks but alsowhite-box ones than convention methods.

Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models