An integrated intrusion detection system using correlation‐based attribute selection and artificial neural network

Abstract Serious concerns regarding vulnerability and security have been raised as a result of the constant growth of computer networks. Intrusion detection systems (IDS) have been adopted by network administrators to provide essential network security. Commercial IDS in the market do not have the capability to identify novel attacks but generate false alarms for legitimate user activities. Neural networks can be applied for the solution of these issues and for providing improved accuracy. Correlation‐based attribute selection ranks the features according to the highest correlation between the attributes and class label. In this article, the authors propose a correlation‐based feature selection integrated with neural network for identifying anomalies. Experimental analysis performed on NSL‐KDD and UNSW‐NB datasets, which are benchmark datasets of intrusion detection with current attacks. The results show that the proposed model is superior in terms of accuracy, sensitivity, and specificity in comparison with some of the state‐of‐the‐art techniques. With the emergence of the Internet of Things Technology, such IDS can be deployed for securing the IoT servers in future. Wireless payment systems can be secured by building and deploying IDS. A secure integrated network management can be achieved which is error‐free and thereby improving performance.