Intrusion detection system based on the beetle swarm optimization and K‐RMS clustering algorithm

• Published in: International journal of adaptive control and signal processing Vol. 38; no. 5; pp. 1675 - 1689
• Main Authors: Pran, S. Gokul, Raja, Sivakami, Jeyasudha, S.
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.05.2024; Wiley Subscription Services, Inc
• Subjects: Accuracy; Algorithms; Artificial neural networks; Classification; Classifiers; Clustering; cyber‐security; Deep learning; Intrusion; intrusion detection; Intrusion detection systems; K‐RMS clustering; Machine learning; Optimization; Recurrent neural networks; Security; Support vector machines
• ISSN: 0890-6327; 1099-1115
• DOI: 10.1002/acs.3771

Summary Intrusion detection is a cyber‐security method that is significant for network security. It is utilized to detect behaviors that compromise security and privacy within a network or in the context of a computer system. To enhance the identification, an Intrusion Detection System Based on the Beetle Swarm Optimization and K‐RMS Clustering Algorithm cluster‐based hybrid classifiers is proposed in this manuscript. Here, the data is amassed from CICIDS2017 dataset. Then the data is preprocessed to eradicate the unwanted noise. After completing the preprocessed data, it can be clustered by using K‐RMS clustering algorithm. This algorithm cluster the entire data to the associated cluster set depending on the data behavior. The classification algorithm is considered to predict the data as normal or attacking behaviors. The hybrid classification is used to predict the data. The solitary predictor aims to achieve high detection rates and accuracy. The hybrid classifiers, such as support vector machines, artificial neural networks are applied to recognize the normal or intruder. The performance of the SVM‐ANN‐IDS method attains 22.05%, 15.87%, 27.25% higher accuracy, 23.90% and 28.53% higher precision, 29.29%, 19.19% and 23.27% higher specificity and 18.28%, 24.36% and 27.49% greater recall when compared to the existing models, like developing novel deep‐learning model to improve network intrusion categorization (DNN‐IDS), Intrusion identification scheme on real‐time data traffic under machine learning techniques along feature selection method (RNN‐SVM‐IDS) and recurrent deep learning basis feature fusion ensemble meta‐classifier for intellectual network intrusion identification scheme (RNN‐IDS) respectively.