Comparative analysis of machine learning algorithms along with classifiers for network intrusion detection

摘要: Intrusion detection is one of the challenging problems encountered by modern network security industry. A has to be continuously monitored for detecting policy violation or suspicious traffic. So an intrusion system needs developed which can monitor any harmful activities and generate results management authority. Data mining play a massive role in development detect intrusion. technique through important information extracted from huge data repositories. In order spot intrusion, traffic created broadly categorized into following two categories- normal anomalous. our proposed paper, several classification techniques machine learning algorithms have been considered categorize Out techniques, we found nine suitable classifiers like BayesNet, Logistic, IBK, J48, PART, JRip, Random Tree, Forest REPTree. algorithms, worked on Boosting, Bagging Blending (Stacking) compared their accuracies as well. The comparison these performed using WEKA tool listed below according certain performance metrics. Simulation models 10-fold cross validation. NSL-KDD based set used this simulation WEKA.