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

Cybersecurity breaches are the common anomalies for distributedcyber-physical systems (CPS). However, the cyber security breach classificationis still a difficult problem, even using cutting-edge artificial intelligence(AI) approaches. In this paper, we study the multi-class classification problemin cyber security for attack detection. A challenging multi-node data-censoringcase is considered. In such a case, data within each data center/node cannot beshared while the local data is incomplete. Particularly, local nodes containonly a part of the multiple classes. In order to train a global multi-classclassifier without sharing the raw data across all nodes, the main result ofour study is designing a multi-node multi-class classification ensembleapproach. By gathering the estimated parameters of the binary classifiers anddata densities from each local node, the missing information for each localnode is completed to build the global multi-class classifier. Numericalexperiments are given to validate the effectiveness of the proposed approachunder the multi-node data-censoring case. Under such a case, we even show theout-performance of the proposed approach over the full-data approach.

CPS Attack Detection under Limited Local Information in Cyber Security: A Multi-node Multi-class Classification Ensemble Approach