Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198571,
        author = {Shaik Mohammed Rizwan and Mohammad Rafeek Khan and Mohiuddin Ali Khan and Mohammad Imran Alam and Huda Fatima and Sarfaraz Ahmed},
        title = {An Intelligent Intrusion Detection System for IoT Networks Using Machine Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {8416-8426},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198571},
        abstract = {The fast development of Internet of Things (IoT) technologies has made networked systems much more susceptible to various and advanced cyber-attacks. Conventional intrusion detection systems (IDS) tend to be insufficient to deal with the dynamic and large-scale nature of an IoT environment. In a bid to address these issues, this paper presents an intelligent machine-learning-driven intrusion detection system that aims at improving the detection accuracy, efficiency, and scalability of the IoT networks. The suggested framework will integrate a complete data processing pipeline, such as data cleaning, encoding features, normalizing features, selecting features, and addressing imbalanced approach with Synthetic Minority Over-Sampling Technique (SMOTE). Several trained machine learning models, i.e. Random Forest, Support Vector machine and Gradient Boosting, are used to effectively classify normal and malicious network traffic. Benchmark datasets, such as UNSW-NB15, TON_IoT, and CICIDS2017, are used to evaluate the system to make sure it is robust and can be generalized to various IoT settings. The experimental findings indicate that the Random Forest model has a better performance with an accuracy of 97.8, a precision of 97.2, a recall of 98.4, and F1-score of 97.8. The ROC curve analysis and confusion matrix evaluation further confirm the performance, as the discrimination ability is high with low rates of false alarms.The findings reveal the usefulness of incorporating data preprocessing, imbalance management, and ensemble learning methods in enhancing intrusion detection performance. The suggested system will offer a scalable and reliable solution to protect IoT networks against numerous forms of cyber threats, such as denial-of-service, probing, and brute force attacks.},
        keywords = {Intrusion Detection System (IDS), Internet of Things (IoT), Machine Learning, Network Security, Cybersecurity, Ensemble Learning, Random Forest, SMOTE, Feature Selection, IoT Security},
        month = {April},
        }