Crow-AFL: Crow Based Adaptive Fractional Lion Optimization Approach for the Intrusion Detection

Abstract

Intrusion detection has played a major role in ensuring the cybersecurity in various networks. Literature works deal with several cyber attacks in the data through designing various supervised approaches, but have not considered the size of the database during the optimization. Since, the data increases in size exponentially, it is necessary to cluster the database before detecting the presence of an intruder in the system. This work has considered these challenges and thus, has introduced a Crow based Adaptive Fractional Lion (Crow-AFL) optimization approach. The proposed intrusion detection system clusters the database into several groups with the Crow-AFL and detects the presence of intrusion in the clusters with the use of the HSDT classifier. Then, the compact data is provided to the deep belief network trained with Crow-AFL for identifying the presence of intrusion in the entire database. The simulation of the proposed Crow-AFL algorithm is done with the DARPA’s KDD cup dataset 1999. The metrics, accuracy, TPR, and TNR, measure the performance of the proposed Crow-AFL algorithm, and it has shown better performance with the value of 96%, 95%, and 96%, respectively.