A new model for intrusion detection systems using bat algorithm

There is a need for an efficient intrusion detection system (IDS) working over the network to detect all possible attacks. Intrusion detection has gained popularity in the last two decades as with the increase in intruder attempts to break into or misuse systems. There are many techniques used in intrusion detection for protecting computers and networks from network-based and host-based attacks. In this work, the proposed approach presents a new model for IDS using bat algorithm that aims to select the best features to find intrusions and utilising big data models. The proposed approach is divided into several phases to extract and find all possible features that directly affect the detection process. The proposed approach is tested using the KNIME Analytics Platform based on support vector machine (SVM) and naive Bayes classifiers. The experiment results gave high accuracy of 97.52% with reducing error classification into 2.47% using the SVM classifier.