DefinePK

Abstract

Mobile Ad hoc Networks (MANETs) are vulnerable to various kinds of threats due to their dynamic nature and lack of a central point of control. Intrusion Detection System (IDS) which can act in collaboration with other IDS nodes in the network is getting popularity due to its faster adaptability to the changes in the behavior of network traffic. A standalone node in MANET will feel very difficult to set any predefined rule for identifying correctly attack traffic since there is no major difference between normal and attack traffic. Hence, in this paper we have proposed an intelligent collaborative model based on data mining for intrusion traffic detection system that can detect attacks. Here we find and deploy friendly nodes in the network that continuously monitors the behavior of other nodes to find nodes or set of nodes exhibiting anomalous behavior. NS-2 simulations were carried out to analyze the performance of the proposed system. We evaluated the performance of our proposed collaborative IDS scheme with various other existing IDS models. The results clearly showed that the proposed intrusion detection system considerably reduces the false positive rate, thereby proving that the proposed technique is capable of identifying anomalies in network better than other existing system.