COMPARATIVE STUDY ON MACHINE LEARNING ALGORITHMS IN INTRUSION DETECTION
Kanakala Swathi, G.Vijaya Lakshmi · Journal of Emerging Technologies and Innovative Research · 2021
In the earlier many years, the quick improvement of Intrusion Detection and Prevention frameworks assumed an urgent part in PCs organization and security. Interruption recognition framework of Intrusion detection system (IDS) is one of the executed arrangements against hurtful assaults. Moreover, assailants consistently continue to change their apparatuses and methods. Notwithstanding, carrying out an acknowledged IDS framework is additionally a difficult errand. In this paper, a few investigations have been performed and assessed to survey different managed learning classifiers dependent on KDD interruption dataset. It prevailed to figure a few presentation measurements to assess the chose classifiers. The attention was on bogus negative and bogus positive execution measurements to upgrade the recognition pace of the interruption discovery framework. The executed analyses showed that the KNN Classifier accomplished the most accurate results in determining the intrusion rate when compared to the other algorithms like SVM (support Vector Machine), DT (Decision Tree), LR (Logistic Regression) and GNB (Gaussion naive Bayes). So, application of KNN classifier while designing the system will give us results in a good way.