AI-Driven Intrusion Detection in IoT Networks: Enhancing Security through Machine Learning and Feature Selection Techniques

DOI

10.2991/978-94-6463-700-7_31How to use a DOI?

Keywords

—IoT Security; Intrusion Detection System (IDS); Machine Learning; Permutation Importance; Feature Selection; Cybersecurity; Anomaly Detection; AI-Driven Security; IoT Networks; Network Traffic Analysis

Abstract

The Internet of Things (IoT) has changed several industries by its rapid spread. It has made automation and seamless communication possible. IoT networks now have serious vulnerabilities as a result of their exponential growth, which makes them easy targets for cyberattacks. The specific issues presented by IoT environments cannot often be adequately addressed by traditional security mechanisms like firewalls and antivirus software. This calls for the development of more advanced security solutions. In this study, an AI-driven intrusion detection system (IDS) that is especially suited for Internet of Things networks is designed and put into operation. The proposed system leverages advanced machine learning algorithms to analyze network traffic and detect anomalies indicative of potential security breaches. To optimize the performance of the IDS, this study employs permutation importance for feature selection, a technique that enhances the interpretability and accuracy of machine learning models by identifying the most relevant features from the dataset. Through a thorough series of tests involving multiple machine learning models, such as Support Vector Machines (SVM), Random Forests, and Neural Networks, the efficacy of the suggested IDS is meticulously assessed. These models are trained and tested on a representative dataset to assess their capability in accurately identifying and mitigating diverse security threats prevalent in IoT networks, such as Distributed Denial of Service (DDoS) attacks, unauthorized access, and malware infiltration. The results of this study demonstrate that the integration of permutation selection in the feature selection process significantly improves the detection accuracy and operational efficiency of the IDS. This research not only contributes to the ongoing efforts in securing IoT infrastructures but also provides valuable insights into the application of machine learning techniques in enhancing the robustness of intrusion detection systems. The results have significant design implications for next-generation intrusion detection systems (IDS) that can protect the quickly growing IoT ecosystem from new cyber threats.

Copyright

© 2025 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  - Karamvir Kharinta
AU  - Kumar Harsh
AU  - Deepak Paramhans
PY  - 2025
DA  - 2025/04/19
TI  - AI-Driven Intrusion Detection in IoT Networks: Enhancing Security through Machine Learning and Feature Selection Techniques
BT  - Proceedings of the International Conference on Advancements in Computing Technologies and Artificial Intelligence (COMPUTATIA-2025)
PB  - Atlantis Press
SP  - 390
EP  - 402
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-700-7_31
DO  - 10.2991/978-94-6463-700-7_31
ID  - Kharinta2025
ER  -