Dynamic malicious node detection with semi-supervised multivariate classification in cognitive wireless sensor networks

摘要

Usually, wireless sensor networks are distributed massively with a number of nodes in an open large-scalernenvironment, and they are vulnerable to malicious attacks because the communications change dynamicallyrnand unpredictably. In this paper, we present a detection method based on multivariate classification to findrnout the malicious sensor nodes. It learns the features of a few type-known node, classifies them with dynamicalrnmultivariate classification, and then establishes the sample space of all sensor nodes in the networkrnactivities to deduce the malicious nodes. The experiment results show that as long as the value of sensorrnnode preferences and the number of active sensor nodes is stable, the false detection rate is stabilized belowrn0.5%. This proves that the algorithm can be used to the cognitive wireless sensor networks widely.