Clustering and Hybrid Genetic Algorithm based Intrusion Detection Strategy

Ad hoc networks face serious security threat due to its inherent weaknesses. Intrusion detection is crucial technology in protecting the security of Ad hoc networks. Recently, Intrusion Detection Systems (IDS) face open issues, such as how to make use of intrusion detection technologies to excavate normal/abnormal behaviors from a lot of initialized data and dig out invasion models later for intrusion detection automatically and effectively. In this paper, we propose an enhanced algorithm combined improved clustering algorithm with Hybrid Genetic Algorithm (HGA), called Enhanced Intrusion Detection Algorithm (EIDA) for intrusion detection in Ad hoc networks. Clustering Algorithm is used to divide the normal/anomalous data from network and system behaviors. Then HGA is used to dig out the invasion rules. Our EIDA is an unsupervised anomaly detection algorithm. The experiment result shows that it is extensible and not sensitive to the sequence of the input data sets. It has the capacity to deal with different types of data and detection rate and false positive rate of intrusion detection has been improved effectively.