A Novel Anomaly-Based Intrusion Detection Model Using PSOGWO-Optimized BP Neural Network and GA-Based Feature Selection

• Published in: Sensors (Basel, Switzerland) Switzerland), 2022-11, Vol.22 (23), p.9318
• Main Authors: Sheikhi, Saeid, Kostakos, Panos
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; anomaly detection; Back propagation; Back propagation networks; Classification; Communication; cybersecurity; Datasets; Detectors; Experiments; Feature selection; Genetic algorithms; Intrusion detection systems; Machine learning; Mathematical optimization; Methods; network intrusion; network intrusion detection; Neural networks; Neural Networks, Computer; Optimization algorithms; Propagation; Reproduction; Safety and security measures; Security software; Support vector machines
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22239318

Intrusion detection systems (IDS) are crucial for network security because they enable detection of and response to malicious traffic. However, as next-generation communications networks become increasingly diversified and interconnected, intrusion detection systems are confronted with dimensionality difficulties. Prior works have shown that high-dimensional datasets that simulate real-world network data increase the complexity and processing time of IDS system training and testing, while irrelevant features waste resources and reduce the detection rate. In this paper, a new intrusion detection model is presented which uses a genetic algorithm (GA) for feature selection and optimization algorithms for gradient descent. First, the GA-based method is used to select a set of highly correlated features from the NSL-KDD dataset that can significantly improve the detection ability of the proposed model. A Back-Propagation Neural Network (BPNN) is then trained using the HPSOGWO method, a hybrid combination of the Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) algorithms. Finally, the hybrid HPSOGWO-BPNN algorithm is used to solve binary and multi-class classification problems on the NSL-KDD dataset. The experimental outcomes demonstrate that the proposed model achieves better performance than other techniques in terms of accuracy, with a lower error rate and better ability to detect different types of attacks.