Intrusion Detection and Classification Using Machine Learning

In the modern society, people increasingly use networks services. Due to rising in attacks and intrusion in network and its consequences and financial losses, Network security is a critical necessity for networks. Intrusion detection systems try to protect the network from illegal access. Abuse detection and anomaly detection are two major types of these systems. In this paper, we propose a machine learning method to detect the intrusions in network. Moreover, the learned model can classify the intrusions into four class, including DoS، U2R، R2L, and prob. NSL-KDD is a standard dataset for intrusions in networks that used in this paper. First, we carried out the feature selection and preprocessing on data to prepare the data for learning phase. Then,a model was developed for intrusion detection using support vector machine (SVM). Experimental results confirm that our method could successfully detect and classify the intrusions in network with accuracy of 99%.

Intrusion Detection Systems; Support Vector Machine; Machine Learning.