A comparative analysis of Network Intrusion Detection (NID) using Artificial Intelligence techniques for increase network security

MD Shadman Soumik *

Department of Information Technology (MSIT), Washington University of Science and Technology (WUST), 2900 Eisenhower Ave, Alexandria, VA 22314.
 
Research Article
International Journal of Science and Research Archive, 2024, 13(02), 4014-4025.
Article DOI: 10.30574/ijsra.2024.13.2.2664
Publication history: 
Received on 19 November 2024; revised on 26 December 2024; accepted on 28 December 2024
 
Abstract: 
Network Intrusion Detection Systems (NIDS) are critical components of modern cybersecurity frameworks, designed to detect and mitigate malicious activities within networks. This study explores the application of Artificial Intelligence (AI) techniques, including Machine Learning (ML) and DL, for improving network security through accurate intrusion detection. Using the CIS-CICIDS2017 dataset, a comprehensive preprocessing pipeline involving data cleaning, SMOTE-based balancing, Min-Max normalization, and feature selection was employed. The Random Forest (RF) model demonstrated superior performance with an accuracy99.90%, precision97.78%, recall97.08%, and an F1-score97.41%. Comparative analysis with Decision Tree (DT), Stacked LSTM, and AdaBoost models highlighted RF's robustness in detecting and classifying network traffic. Future research aims to optimize feature engineering and explore hybrid AI models for improved real-time intrusion detection in dynamic network environments.
 
Keywords: 
NIDS; Artificial Intelligence; Machine Learning Algorithm; Random Forest Algorithm; Cyber Security; CICIDS2017
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0