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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The advent of 6G/NextG networks comes along with a series of benefits,including extreme capacity, reliability, and efficiency. However, thesenetworks may become vulnerable to new security threats. Therefore, 6G/NextGnetworks must be equipped with advanced Artificial Intelligence algorithms, inorder to evade these attacks. Existing studies on the intrusion detection taskrely on the train of shallow machine learning classifiers, including LogisticRegression, Decision Trees, and so on, yielding suboptimal performance. Othersare based on deep neural networks consisting of static components, which arenot conditional on the input. This limits their representation power andefficiency. To resolve these issues, we present the first study integratingMixture of Experts (MoE) for identifying malicious traffic. Specifically, weuse network traffic data and convert the 1D array of features into a 2D matrix.Next, we pass this matrix through convolutional neural network (CNN) layersfollowed by batch normalization and max pooling layers. After obtaining therepresentation vector via the CNN layers, a sparsely gated MoE layer is used.This layer consists of a set of experts (dense layers) and a router, where therouter assigns weights to the output of each expert. Sparsity is achieved bychoosing the most relevant experts of the total ones. Finally, we perform aseries of ablation experiments to prove the effectiveness of our proposedmodel. Experiments are conducted on the 5G-NIDD dataset, a network intrusiondetection dataset generated from a real 5G test network. Results show that ourintroduced approach reaches weighted F1-score up to 99.95% achieving comparableperformance to existing approaches. Findings also show that our proposed modelachieves multiple advantages over state-of-the-art approaches.

Convolutional Neural Networks and Mixture of Experts for Intrusion Detection in 5G Networks and beyond