Multi-agent trust-based intrusion detection scheme for wireless sensor networks

摘要

In order to achieve both a higher detection rate and a lower false positive rate of internal node intrusion detection in layer-cluster wireless sensor networks, an intrusion detection scheme based on the use of both a multi-agent system and a node trust value is proposed. In this scheme, the multi-agent model framework is established in both the cluster heads and the ordinary sensor nodes to perform intrusion detection. First, various, typical node trust attributes are defined and Mahalanobis distance theory is used to judge whether these attributes are normal. Second, the node trust value is calculated and updated based on the combination of the Beta distribution and a tolerance factor. Finally, node intrusion detection is realized. Simulation results demonstrate that the modified scheme has a higher detection rate and a lower false positive rate, even when several types of intrusions are present. (C) 2017 Elsevier Ltd. All rights reserved.