As known that most people in recent years become depend on the Internet in most things in their life, Now-a-days people rely on networks to send and receive emails, banking online system, stock price and online shopping. The excessive use of the communication networks leads to make important and secret information suspected to attacker, and the number of attacks on the important information over the internet is increasing daily. Intrusion is one of the main threats to the internet. Hence security issues had been big problem, so that various techniques and approaches have been presented to address the limitations of intrusion detection system such as low accuracy, high false alarm rate, and time consuming. This research proposed a hybrid machine learning technique for network intrusion detection based on combination of K-means clustering and Sequential Minimal Optimization (SMO) classification. The aim of this research is to introduce novel approach that able to reduce the rate of false positive alarm, to improve the detection rate and detect zero-day attackers and to get high accuracy for classify intrusion. The NSL-KDD dataset has been used to evaluate the proposed technique. In order to improve classification performance, some steps have been taken on the dataset like feature selection. The classification has been performed by using (Sequential Minimal Optimization SMO + K-mean clustering). After training and testing the proposed hybrid machine learning technique, the results have shown that the proposed technique (K-mean + SMO) has achieved a positive detection rate, reduce the false alarm rate and get high accuracy.
Table of Contents