Biblio

Vehicular networks are susceptible to variety of attacks such as denial of service (DoS) attack, sybil attack and false alert generation attack. Different cryptographic methods have been proposed to protect vehicular networks from these kind of attacks. However, cryptographic methods have been found to be less effective to protect from insider attacks which are generated within the vehicular network system. Misbehavior detection system is found to be more effective to detect and prevent insider attacks. In this paper, we propose a machine learning based misbehavior detection system which is trained using datasets generated through extensive simulation based on realistic vehicular network environment. The simulation results demonstrate that our proposed scheme outperforms previous methods in terms of accurately identifying various misbehavior.

Mobile ad hoc networks (MANET) is a type of networks that consists of autonomous nodes connecting directly without a top-down network architecture or central controller. Absence of base stations in MANET force the nodes to rely on their adjacent nodes in transmitting messages. The dynamic nature of MANET makes the relationship between nodes untrusted due to mobility of nodes. A malicious node may start denial of service attack at network layer to discard the packets instead of forwarding them to destination which is known as black hole attack. In this paper a secure and trust based approach based on ad hoc on demand distance vector (STAODV) has been proposed to improve the security of AODV routing protocol. The approach isolates the malicious nodes that try to attack the network depending on their previous information. A trust level is attached to each participating node to detect the level of trust of that node. Each incoming packet will be examined to prevent the black hole attack.