Network intrusion detection leveraging machine learning and feature selection

Arshid Ali, Shahtaj Shaukat, Muhammad Tayyab, Muazzam A. Khan, Jan Sher Khan, Arshad, Jawad Ahmad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)
5 Downloads (Pure)

Abstract

Handling superfluous and insignificant features in high-dimension data sets incidents led to a long-term demand for system anomaly detection. Ignoring such elements with spectral instruction not speeds up the analysis process but again facilitates classifiers to make accurate selections during attack perception stage, when wrestling with huge-scale and heterogeneous data. In this paper, for dimensionality reduction of data, we use Correlation-based Feature Selection (CFS) and Naïve Bayes (NB) classifier techniques. The proposed Intrusion Detection System (IDS) classifies attacks using a Multilayer Perceptron (MLP) and Instance-Based Learning algorithm (IBK). The accuracy of the introduced IDS is 99.87% and 99.82% with only 5 and 3 features out of 78 features for IBK. Other metrics such as precision, Recall, F-measure, and Receiver Operating Curve (ROC) also confirm the principal performance of IBK compared to MLP.
Original languageEnglish
Title of host publication2020 IEEE 17th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET)
PublisherIEEE
Pages49-53
Number of pages5
ISBN (Electronic)9780738105277
ISBN (Print)9781665423007
DOIs
Publication statusPublished - 21 Jan 2021
EventIEEE 17th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI - Online
Duration: 14 Dec 202016 Dec 2020
https://honet-ict.org/archives/honet20/index.html (Link to conference website)

Publication series

Name
ISSN (Print)1949-4092
ISSN (Electronic)1949-4106

Conference

ConferenceIEEE 17th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI
Abbreviated titleIEEE HONET 2020
Period14/12/2016/12/20
Internet address

Keywords

  • intrusion detection system (IDS)
  • correlation-based feature (CFS)
  • classifier subset evaluation
  • multilayer perceptron (MLP)
  • instance-based learning algorithm (IBK)

ASJC Scopus subject areas

  • Information Systems and Management
  • Artificial Intelligence
  • Information Systems
  • Energy Engineering and Power Technology
  • Computer Networks and Communications
  • Computer Science Applications
  • Renewable Energy, Sustainability and the Environment

Fingerprint

Dive into the research topics of 'Network intrusion detection leveraging machine learning and feature selection'. Together they form a unique fingerprint.

Cite this