Poster: A neural network based cluster ensemble approach for anomaly detection in dynamic weighted graphs

Diya Thomas, Rajan Shankaran

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Wireless sensor networks (WSNs) plays a vital role in a variety of service-critical surveillance applications. These applications’ Quality of Service (QoS) requirements can only be met if the network is tolerant to unexpected failures of sensor nodes. Such failures are primarily caused by active security attacks. This paper models the problem of detecting such attacks as an anomaly detection problem in a dynamic graph. We utilize a neural network-based cluster ensemble approach called the Neural network-based K-Mean Spectral and Hierarchical (NKSH) approach to solve the problem. The preliminary experimental results show that this approach can detect such attacks with a high degree of accuracy and precision.

Original languageEnglish
Title of host publicationInternational Conference on Embedded Wireless Systems and Networks, EWSN 2021
EditorsPolly Huang, Marco Zuniga, Guoliang Xing, Chiara Petrioli
Place of PublicationNew York, NY
PublisherAssociation for Computing Machinery
Pages1-2
Number of pages2
ISBN (Print)9780994988652
Publication statusPublished - 2021
EventInternational Conference on Embedded Wireless Systems and Networks, EWSN 2021 - Delft, Netherlands
Duration: 17 Feb 202119 Feb 2021

Publication series

NameInternational Conference on Embedded Wireless Systems and Networks
ISSN (Electronic)2562-2331

Conference

ConferenceInternational Conference on Embedded Wireless Systems and Networks, EWSN 2021
Country/TerritoryNetherlands
CityDelft
Period17/02/2119/02/21

Keywords

  • Anomaly detection
  • DoS
  • Dynamic Graph
  • Security
  • WSN

Fingerprint

Dive into the research topics of 'Poster: A neural network based cluster ensemble approach for anomaly detection in dynamic weighted graphs'. Together they form a unique fingerprint.

Cite this