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

Capsule network is a type of neural network that uses the spatialrelationship between features to classify images. By capturing the poses andrelative positions between features, its ability to recognize affinetransformation is improved, and it surpasses traditional convolutional neuralnetworks (CNNs) when handling translation, rotation and scaling. The StackedCapsule Autoencoder (SCAE) is the state-of-the-art capsule network. The SCAEencodes an image as capsules, each of which contains poses of features andtheir correlations. The encoded contents are then input into the downstreamclassifier to predict the categories of the images. Existing research mainlyfocuses on the security of capsule networks with dynamic routing or EM routing,and little attention has been given to the security and robustness of the SCAE.In this paper, we propose an evasion attack against the SCAE. After aperturbation is generated based on the output of the object capsules in themodel, it is added to an image to reduce the contribution of the objectcapsules related to the original category of the image so that the perturbedimage will be misclassified. We evaluate the attack using an imageclassification experiment, and the experimental results indicate that theattack can achieve high success rates and stealthiness. It confirms that theSCAE has a security vulnerability whereby it is possible to craft adversarialsamples without changing the original structure of the image to fool theclassifiers. We hope that our work will make the community aware of the threatof this attack and raise the attention given to the SCAE's security.

An Evasion Attack against Stacked Capsule Autoencoder