A Simple and Effective Intrusion Detection System for Manets
M V D S Krishna Murty1, Lakshmi Rajamani2
1M V D S Krishna Murty, Research Scholar, Department of Computer Science and Engineering, Jawaharlal Nehru Technological University, Hyderabad (Telangana), India.
2Dr. Lakshmi Rajamani, Professor and Head (Retd), Department of Computer Science and Engineering, Osmania University, Hyderabad (Telangana), India.
Manuscript received on 31 January 2023 | Revised Manuscript received on 06 February 2023 | Manuscript Accepted on 15 February 2023 | Manuscript published on 28 February 2023 | PP: 1-8 | Volume-10 Issue-2, February 2023 | Retrieval Number: 100.1/ijies.B10770210223 | DOI: 10.35940/ijies.B1077.0210223
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This work proposes a simple and effective Intrusion Detection System (IDS) to classify different attacks in MANETs. IDS extracts four features for every traffic pattern and applies the Support Vector Machine algorithm to them for classification. Before using the feature extraction, the input traffic pattern is subjected to pre-processing, as it is composed of non-uniform features. IDS classifies the input traffic pattern into three classes: normal, blackhole, and wormhole. Finally, this work analyses the feasibility of machine learning algorithms for detecting security attacks in MANETs. For experimental validation, we have referred to a self-created dataset acquired from observations of the traffic patterns of nodes attacked by black holes and wormholes. Moreover, we have also validated the proposed method through the NSL-KDD dataset.
Keywords: Intrusion Detection System, Preprocessing, Feature Extraction, Support Vector Machine, Self-Created Dataset.
Scope of the Article: Machine Learning