,
Research Scholar, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation , Guntur , India
,
Professor, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation , Guntur , India
Professor, Gokaraju Rangaraju Institute of Engineering and Technology , Hyderabad , India
The rapid growth of cloud-based and large-scale network infrastructures has increased the complexity and frequency of cyber-attacks, demanding efficient and scalable intrusion detection systems (IDS). This paper will also attempt to create a better Network Intrusion Detection System (NIDS) by incorporating a Hybrid Median Attribute Clustering model with Particle Swarm Optimization (MAHC-PSO) to achieve better detection accuracy, less false alarms, and better computation efficiency in high dimensional network space. The suggested MAHC-PSO model utilizes Information Gain in the feature selection on the KDD Cup’99 dataset to minimize dimensions without losing important network features. The median attribute analysis is used to make data representation in a way that is effective and hybrid hierarchical clustering is used to cluster network traffic patterns. Clustering quality is optimized with the help of particle Swarm Optimization that improves the position of the particles depending on the accuracy of detection and the degree of compactness of the cluster. The performance assessment is done with different network sizes between 10, 000 and 60,000 nodes and compared with the current NWFSF-IDMLM and HO-CNN-LSTM-IDS models. The experimental findings indicate that MAHC-PSO model is always better in all the metrics than the benchmark models. The accuracy of feature extraction, hybrid clustering, and cluster set generation were 98.5%, 98.2% and 98.6%, respectively, with 60,000 nodes. PSO fitness value estimation rate was at its highest of 98.8 and median attribute estimation time was lower, at 18 units and pattern analysis time was lower, at 12 units. The overall intrusion detection accuracy was 98.6 which is very high compared to models. The MAHC-PSO model provides a scalable, efficient, and powerful intrusion detection system in large networks in real-time. Its superior accuracy and reduced processing time make it suitable for deployment in cloud-based, enterprise, and future distributed IT environments.
This is an open access article distributed under the Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
0
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.