The Detection of Network Intrusion Based on Improved Adaboost Algorithm

Abstract

Network intrusion detection is a detection technology which is based on the characteristics of network behavior. In recent years, network intrusion detection, as a research focus in the field of information security, had a rapid development. Redundant and irrelevant features in data have caused a long-term problem in network traffic classification. These features not only slow down the process of classification but also prevent a classifier from making accurate decisions, especially when coping with big data. In this paper, an improved binary particle swarm optimization (BPSO) was proposed to remove redundant features. This method can compress data volumes and reduce the detection time. On this basis, weight adjustment strategies of Adaboost algorithm are improved to alleviate the phenomenon of over-fitting. The performance of the improved Adaboost classifier is evaluated using two intrusion detection evaluation datasets, namely KDD Cup 99 and NSL-KDD dataset. The evaluation results show that our approach has lower false alarm rate, higher accuracy rate and F-Score.