Smart intrusion detection system for MANET

Mobile Ad hoc networks (MANET) are infrastructure less networks which consist of self organized & self configured multihop nodes. The topology of these networks change with time. The nodes in the network not only act as routers but also as hosts. Two main issues in MANET are challenging namely, optimized routing and security. The approach followed in this paper suggests use of data mining techniques such as clustering and classification in developing intrusion detection system for MANET. We will use Zone routing protocol (ZRP) for packet flow which is hybrid in nature. Then various properties of the malicious, selfish and loyal nodes are used to identify the cluster heads. Cluster head is one of the loyal nodes which are having sufficient energy to transmit the message in the mobile Ad hoc networks and also guarantees successful transmission of data from source to destination.