CVS-FLN: a novel IoT-IDS model based on metaheuristic feature selection and neural network classification model

• Published in: Multimedia tools and applications Vol. 83; no. 39; pp. 86557 - 86591
• Main Authors: Geetha, R., Jegatheesan, A., Dhanaraj, Rajesh Kumar, Vijayalakshmi, K., Nayyar, Anand, Arulkumar, V., Velmurugan, J., Thavasimuthu, Rajendran
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2024; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Artificial neural networks; Classification; Computer Communication Networks; Computer Science; Cybersecurity; Data Structures and Information Theory; Datasets; Feature selection; Heuristic methods; Internet of Things; Intrusion detection systems; Machine learning; Multimedia Information Systems; Network reliability; Neural networks; Special Purpose and Application-Based Systems; Feature Selection; CICIDS-2017; Intrusion Detection; CVS; BoT-IoT; FLN; IoT-IDS
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-024-19617-7

The Internet of Things (IoT) is one of the technologies that will be used all over the world in the future, and its security and privacy features are the primary concerns. However, the most critical limitation to overcome before the IoT's widespread use is addressing its security concerns. One of the most critical tasks to address the security problems posed by the IoT is the detection of network intrusions. Intrusion Detection Systems (IDS) for the IoT face substantial challenges because of the functional and physical diversity of the devices. In the rapidly growing IoT industry, the use of IDS is essential for ensuring security since many devices communicate efficiently. IDS are crucial for continual monitoring and responding to any security risks, ensuring the integrity and reliability of interconnected IoT networks. The primary objective of this research is to develop a feature-selection-based intrusion classification model. Therefore, we develop an IoT-IDS feature selection-based classification model to detect intrusions. We propose a metaheuristic algorithm, the Chaotic Vortex Search (CVS) algorithm, for feature selection. The Fast-Learning Network (FLN), an artificial neural network (ANN) model, is additionally proposed for classification. We use the IDS datasets, such as CIC IDS-2017 and BoT-IoT, to evaluate our research model. To test and validate the proposed model, extensive experiments were performed, and the outcomes stated that the CVS-FLN model achieved 99.77% accuracy, 99.92% specificity, 99.60% precision, 99.81% detection rate, and a 99.72% F1-score in the CIC IDS dataset, and 99.68% accuracy, 99.30% precision, 99.83% specificity, 99.11% detection rate, and a 99.21% F1-score in evaluating the BoT-IoT dataset.