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{203605,
        author = {Goury Vishwakarma and Swati Khanve},
        title = {Intelligent Network Intrusion Detection for IoT Systems Based on Machine Learning: A Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {11172-11179},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203605},
        abstract = {The fast proliferation of the Internet of Things (IoT) has generated substantial security issues owing to the enormous number of networked and resource-constrained devices. IoT networks are very susceptible to cyber-attacks that include Distributed Denial of Service (DDoS), botnet infiltration, malware dissemination, and unauthorized access. Traditional security techniques are generally inadequate in IoT systems because of scalability and performance restrictions. As a consequence, intelligent Intrusion Detection Systems (IDS) based on Machine Learning (ML) & Deep Learning (DL) have emerged as viable alternatives. An extensive investigation of ML- & DL-based intrusion detection methods for IoT systems is provided in this article. It examines IDS structures, detection algorithms, widely used datasets, feature engineering methods, and performance assessment measures. Recent developments using Convolutional Neural Network (CNNs), which have shown better performance in identifying intricate and multi-class threats in IoT settings, are highlighted. The report also discusses present obstacles and potential research areas for establishing strong and scalable IoT security solutions. Furthermore, with the emergence of 6G communication networks enabling ultra-high-speed connectivity and massive IoT deployments, intrusion detection systems must become more scalable and computationally efficient. In this review, special emphasis is placed on Convolutional Neural Network (CNN)-based architectures due to their superior capability in detecting intricate, multi-class, and blended IoT attacks.},
        keywords = {Internet of Things, Intrusion Detection System, ML, Deep Learning, CNN, IoT Security},
        month = {May},
        }