Ajou University repository

Poster: Dynamic Clustered Federated Framework for Multi-domain Network Anomaly Detection
Citations

SCOPUS

0

Citation Export

Publication Year
2023-12-05
Journal
CoNEXT Companion 2023 - Companion of the 19th International Conference on emerging Networking EXperiments and Technologies
Publisher
Association for Computing Machinery, Inc
Citation
CoNEXT Companion 2023 - Companion of the 19th International Conference on emerging Networking EXperiments and Technologies, pp.71-72
Keyword
clusteringfederated learningmulti-domainnetwork anomaly detection
Mesh Keyword
ClusteringsData distributionDifferent domainsFederated learningInference modelsLearn+Multi-domainsMultidomain networksNetwork anomaly detectionSub-optimal performance
All Science Classification Codes (ASJC)
Computer Networks and CommunicationsComputer Science ApplicationsHardware and Architecture
Abstract
Federated learning as a distributed category yields sub-optimal performance for the presence of Non-iid in multi-domain data. To this end, we proposes a novel clustered federated framework for unsupervised multi-domain network anomaly detection, which implements dynamic clustered federated based on the data distribution of different domain so that each edge user learns the domain-optimized inference model. Compared to baseline, the proposed method enables users to obtain domain-optimal performance.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36994
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85183588937&origin=inward
DOI
https://doi.org/10.1145/3624354.3630086
Journal URL
http://dl.acm.org/citation.cfm?id=3624354
Type
Conference
Funding
This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2023-2018-0-01431) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation).
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Roh, Byeong-hee Image
Roh, Byeong-hee노병희
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.