Light Weight Prediction Algorithm Based IDS for Wireless Sensor Networks

摘要

Wireless sensor networks when deployed in an unmanned environment to monitor the surroundings are prone to various security threats. Threats go severe in case of hierarchical WSN where the powerful cluster heads gets attacked thereby affecting the entire cluster. These hierarchical WSN are prone to various denial of service attacks such as black hole, gray hole, sybil, wormhole, flooding, etc. DoS attacks occur in the network layer during routing process; hence, they are also called as routing layer attacks. These Denial of Service (DoS) attacks try to spoof, falsify or drop the packets during the packet routing process. They may even flood the network with unwanted data packets. If anyone cluster head is captured and made malicious, the entire cluster member nodes beneath the cluster get affected. On the other hand, if the cluster member nodes are malicious due to the broadcast wireless communication between all the source nodes it can disrupt the entire cluster functions. Thereby, a scheme which can detect both the malicious cluster member and cluster head is the current need. To serve this purpose, a learning based prediction algorithm is proposed. Thus, a prediction based Intrusion Detection Scheme (IDS) to detect the malicious nodes is proposed and simulations were carried out using NS2 Mannasim framework. Simulation results prove the performance of the proposed work by achieving good detection ratio and less false positive.