Efficient Hybrid Model for Intrusion Detection Systems

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

Abstract

This paper proposes a new hybrid ML model that relies on K-Means clustering and the Variational Bayesian Gaussian Mixture models to efficiently detect and classify unknown network attacks. The proposed model first classifies the input data into various clusters using K-Means. Then, it identifies anomalies in those clusters using the Variational Bayesian Gaussian Mixture model. The model has been tested against the CICIDS 2017 dataset that contains new relevant attacks and realistic normal traffic, with a reasonable size. To balance the data, undersampling techniques were used. Furthermore, the features were reduced from 78 to 28 using feature selection and feature extraction methods. The proposed model shows promising results when identifying whether a data point is an attack or not with an F1 score of up to 91%.

Original languageEnglish
Title of host publicationSECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography
EditorsSabrina De Capitani di Vimercati, Pierangela Samarati
PublisherScience and Technology Publications, Lda
Pages694-700
Number of pages7
ISBN (Print)9789897585906
DOIs
Publication statusPublished - 1 Jan 2022
Event19th International Conference on Security and Cryptography, SECRYPT 2022 - Lisbon, Portugal
Duration: 11 Jul 202213 Jul 2022

Publication series

NameProceedings of the International Conference on Security and Cryptography
Volume1
ISSN (Print)2184-7711

Conference

Conference19th International Conference on Security and Cryptography, SECRYPT 2022
Country/TerritoryPortugal
CityLisbon
Period11/07/2213/07/22

Keywords

  • Bayesian Model
  • Hybrid Approach
  • IDS
  • K-Means
  • Supervised and Unsupervised Learning

Fingerprint

Dive into the research topics of 'Efficient Hybrid Model for Intrusion Detection Systems'. Together they form a unique fingerprint.

Cite this