A self-adaptive intrusion detection method for AODV-based mobile ad hoc networks

Mobile ad hoc networks (MANET) are usually formed without any major infrastructure. As a result, they are relatively vulnerable to malicious network attacks and therefore the security is a more significant issue than in infrastructure-type wireless networks. In these networks, it is difficult to identify malicious hosts, as the topology of the network changes dynamically. A malicious host can easily interrupt a route for which the malicious host is one of the forming nodes in the communication path. In the literature, there are several proposals to detect such malicious host inside the network. In those methods usually a baseline profile is defined in accordance to static training data and then they are used to verify the identity and the topology of the network, thus avoiding any malicious host to be joined in the network. Since the topology of a MANET is dynamically changing, use of a static profile is not efficient. In this paper, we propose a new intrusion detection scheme based on a learning process, so that the training data can be updated at particular time intervals. The simulation results show the effectiveness of the proposed technique compared to conventional schemes