Intrusion detection based on machine learning and statistical feature ranking techniques

Big data has made it easier for people to live an information-based Internet lifestyle, but it has also created several serious network security issues that make it difficult to use networks regularly. At the moment, intrusion detection systems are mostly used to identify aberrant network traffic. So, utilizing a Machine Learning (ML) technique, we suggested a statistical analysis-based intrusion detection system. In this paper, we suggested an intrusion detection system using the statistical analysis of the ranking method known as the T-test: two samples assuming unequal variances. A substantial amount of network traffic data that includes both malware data and normal traffic data is gathered to be able to identify the pattern of the malware data. Nine different traffic features for both intrusion and normal traffic are extracted and further ranked using the t-test, yielding nine "t" values from which various features were derived. The Naive Bayes machine learning algorithm will then be applied to the 9 features, deleting one feature at a time that has the lowest "t" value to provide 9 alternative accuracy values. After examining the accuracy value, we get to the conclusion that the two features with the lowest value are removed to attain the highest accuracy, i.e., 95.69% with the top 7 features rather than using all 9 features.