Advanced Feature-Selection-Based Hybrid Ensemble Learning Algorithms for Network Intrusion Detection Systems

As cyber-attacks become remarkably sophisticated, effective Intrusion Detection Systems (IDSs) are needed to monitor computer resources and provide alerts regarding unusual or suspicious behavior. Despite using several machine learning (ML) data mining methods achieve high effectiveness, these systems have not proven ideal. Current intrusion detection algorithms suffer from dimensionality, redundancy, meaningless data, error rate, false alarm false-negative rate. This paper proposes a novel Ensemble Learning (EL) algorithm-based network IDS model. The efficient feature selection is attained via hybrid of Correlation Feature Selection coupled with Forest Panelized Attributes (CFS–FPA). improved involves exploiting AdaBoosting bagging ensemble modify four classifiers: Support Vector Machine, Random Forest, Naïve Bayes, K-Nearest Neighbor. These enhanced classifiers been applied first as then bagging, the aggregation technique through voting average technique. To better benchmarking, both binary multi-class classification forms used evaluate experimental results applying model CICIDS2017 dataset achieved promising 99.7%accuracy, 0.053 0.004 system will be for information technology-based organizations, it expected level symmetry between security attacks malicious intrusion.