WIRELESS INTRUSION DETECTION SYSTEM-BASED ON NEURAL NETWORK APPROACHES

Authors

Ammar Ali Mohammed Ridha Information Systems department, Directorate of Communication and Information Technology, Ministry of Interior, Baghdad, Iraq

Keywords:

Intrusion detection system, neural networks, dataset, preprocessing

Abstract

Wireless network security is crucial to privacy, especially when sensitive data is exchanged across it. Most systems now use modern online services for government, banking, email, and marketing, making this issue more important. After completing the preparatory processing of the chosen data set, numerous methods were utilized to reduce the total number of features in forming the neural network classifier. In addition to training and testing the system, we also examined the accuracy of the classifier and the detection and error rates based on the Matlab program. The findings of practical experiments indicate that the performance improved when relying on the data set with reduced features rather than the data set with full features. This resulted in improved Detection rates and low positive error rates for all five offensive classes in addition to the natural class. The system has attained an average level of accuracy in determining what constitutes offensive communication and what constitutes normal conversation % 99.7. The system has been evaluated using the KDDCup99 standard data set, which is widely used in the field of intrusion detection research by a large number of researchers as well as others who are interested in this field.

References

A. Khraisat, I. Gondal, P. Vamplew, and J. Kamruzzaman, "Survey of intrusion detection systems: techniques, datasets and challenges," Cybersecurity, vol. 2, no. 1, pp. 1-22, 2019.

H.-J. Liao, C.-H. R. Lin, Y.-C. Lin, and K.-Y. Tung, "Intrusion detection system: A comprehensive review," Journal of Network and Computer Applications, vol. 36, no. 1, pp. 16-24, 2013.

N. Shabani and A. Munir, "A review of cyber security issues in hospitality industry," in Intelligent Computing: Proceedings of the 2020 Computing Conference, Volume 3, 2020, pp. 482-493: Springer.

S. Shakya and B. R. Kaphle, "Intrusion detection system using back propagation algorithm and compare its performance with self organizing map," Journal of Advanced College of Engineering and Management, vol. 1, pp. 127-138, 2015.

O. T. Akinwande and M. B. Abdullahi, "Performance Evaluation of Artificial Immune System Algorithms for Intrusion Detection," 2019.

V. Gowdhaman and R. Dhanapal, "An intrusion detection system for wireless sensor networks using deep neural network," Soft Computing, pp. 1-9, 2021.

H. Wang, Z. Cao, and B. Hong, "A network intrusion detection system based on convolutional neural network," Journal of Intelligent & Fuzzy Systems, vol. 38, no. 6, pp. 7623-7637, 2020.

A. Abbas, M. A. Khan, S. Latif, M. Ajaz, A. A. Shah, and J. Ahmad, "A new ensemble-based intrusion detection system for internet of things," Arabian Journal for Science and Engineering, pp. 1-15, 2021.

A. Amouri, V. T. Alaparthy, and S. D. Morgera, "A machine learning based intrusion detection system for mobile Internet of Things," Sensors, vol. 20, no. 2, p. 461, 2020.

S. P. Thirimanne, L. Jayawardana, L. Yasakethu, P. Liyanaarachchi, and C. Hewage, "Deep neural network based real-time intrusion detection system," SN Computer Science, vol. 3, no. 2, p. 145, 2022.

Downloads

Published

2024-01-30

How to Cite

Ammar Ali Mohammed Ridha. (2024). WIRELESS INTRUSION DETECTION SYSTEM-BASED ON NEURAL NETWORK APPROACHES. European Journal of Research Development and Sustainability, 5(1), 77-81. Retrieved from https://scholarzest.com/index.php/ejrds/article/view/4255