Home // EMERGING 2024, The Sixteenth International Conference on Emerging Networks and Systems Intelligence // View article

Network Intrusion Detection Using Machine Learning Processes

Authors:
Nader Mir
Akshatha Pramod
Meghna Shankar

Keywords: Network Security; Network Intrusion Detection System; Machine Learning; XGBoost; Random Forest; Recurrent Neural Networks; ToN_IoT Dataset.

Abstract:
Network security methods must work towards preventing data breaches as we have entered the growing era of technology. This paper provides a work-in-progress computer network security study in which the network’s security capability has been enhanced by using Machine Learning (ML)-assisted intrusion detection system. The goal of the paper is to present a study on improving network intrusion detection systems by incorporating machine learning techniques. We specifically focus on the accuracy and overall performance of two ML algorithms, Random Forest and XGBoost. We introduce this study when ML is incorporated in an existing network infrastructure specifically within the network monitoring and analysis components. The network performance is centered around the two algorithms. These algorithms are deployed on an available dataset named the TON_IoT and compared based on accuracy and overall performance thus providing an analysis of the effectiveness of these models in detecting network intrusions.

Pages: 1 to 5

Copyright: Copyright (c) IARIA, 2024

Publication date: September 29, 2024

Published in: conference

ISSN: 2326-9383

ISBN: 978-1-68558-188-6

Location: Venice, Italy

Dates: from September 29, 2024 to October 3, 2024