Dynamic Malicious Node Detection With Semi-supervised Multivariate Classification In Cognitive Wireless Sensor Networks

Usually, wireless sensor networks are distributed massively with a number of nodes in an open large-scale environment, and they are vulnerable to malicious attacks because the communications change dynamically and unpredictably. In this paper, we present a detection method based on multivariate classification to find out the malicious sensor nodes. It learns the features of a few type-known node, classifies them with dynamical multivariate classification, and then establishes the sample space of all sensor nodes in the network activities to deduce the malicious nodes. The experiment results show that as long as the value of sensor node preferences and the number of active sensor nodes is stable, the false detection rate is stabilized below 0.5%. This proves that the algorithm can be used to the cognitive wireless sensor networks widely. Copyright © 2014 John Wiley & Sons, Ltd.