Hybrid Anomaly Detection using K-Means Clustering in Wireless Sensor Networks
- Mohammad Wazid
- IACR Cryptology ePrint Archive
Wireless Sensor Network (WSN) has a great potential to be deployed in wide range of applications like consumer, industrial and defense sectors. WSNs are susceptible to various attacks, in which misdirection a kind of Denial of Service (DoS) attack is very difficult to detect and defend. In misdirection attack, the intruder misdirects the incoming packets to a node other than the intended node. Due to this attack, high end- to- end delay (sometimes infinite) is introduced in the network and performance of the network (i.e. throughput) is degraded. In this paper we have done a topological analysis of WSN in the presence of misdirection attack and presented an algorithm for the prediction of delay and throughput. We observed that WSN performs better for tree network topology as compared to mesh topology.