A secure framework for BeeAdHoc (Bio/Nature inspired MANET routing protocol) using Neural Networks

Abstract

A mobile ad hoc network (MANET) is a group of mobile nodes that are formed dynamically and communicate with each other via wireless links. These networks are characterized by dynamic topology, the absence of central authorities, distributed cooperation, and constrained capability. Thus, they are vulnerable to a number of security threats. These vulnerabilities create significant challenges for routing protocols. Bio/Nature-inspired routing algorithms such as BeeAdHoc have been o_ered for developing routing algorithms for MANETs. But a malicious node can seriously disrupt the routing behavior of this protocol. In this paper, we try to build a security protocol for BeeAdHoc which utilizes the Back Propagation Network (BPN). A backpropagation neural network is used for the purpose of anomaly detection. For simulating, we use the TrueTime toolbox of MATLAB. The results of our experiments show that our proposed protocol is able to counter the different types of threats.