An approach system detection intrusion for an IOT-based learning system

DOI

10.2991/978-94-6463-360-3_35How to use a DOI?

Keywords

Internet of Things; intrusion detection system; MLP; SVM; SS; Kddcup’9

Abstract

The Internet of Things (IoT) is a network of objects connected to the Internet, which enable data to be collected, shared and used. They are often low-powered devices with limited resources, making them vulnerable to a variety of attacks due to their interconnected nature and lack of network security or data leakage. So, detecting and preventing intrusions into an IoT environment has become paramount. This work creates an Intrusion Detection System (IDS) based on two Machine Learning techniques. The reduction of the dimensionality algorithm method concerning the sample selection (SS) of our system was identified by comparing the vector machine (SVM) and the multilayer perceptron (MLP). These results led us to consider SS techniques for the MLP classifier in order to fill this gap and further improve performance. Indeed, the results exceeded those of SVM. This proves the effectiveness of SS methods in increasing generalization capacity. We carried out a thorough and comprehensive study of the descriptive statistics of the data. As a result, we were able to detect dependency relationships between variables, while categorizing them. This analysis enabled us to identify the most important variables. By applying SVM to the variables selected in the previous step (descriptive statistics), we were finally able to maintain good performance while significantly reducing computational costs.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Admeur Smail
AU  - Alaoui Souad
AU  - Haddani Outman
AU  - Amjad Souad
AU  - Attariuas Hicham
PY  - 2024
DA  - 2024/02/05
TI  - An approach system detection intrusion for an IOT-based learning system
BT  - Proceedings of the E-Learning and Smart Engineering Systems (ELSES 2023)
PB  - Atlantis Press
SP  - 352
EP  - 363
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6463-360-3_35
DO  - 10.2991/978-94-6463-360-3_35
ID  - Smail2024
ER  -