A stochastic learning automata-based solution for intrusion detection in vehicular ad hoc networks

作者：Misra Sudip^*; Krishna P Venkata; Abraham Kiran Isaac

来源：Security and Communication Networks, 2011, 4(6): 666-677.

DOI：10.1002/sec.200

• VANET
• traffic management
• intrusion detection
• learning automata

A number of security concerns are associated with vehicular ad hoc networks (VANET) - some primarily related with the transmission issues between the vehicles and the base stations, while others related with the privacy of the end- users. Security in VANET is of significant importance, considering the scale of the possible deployment of VANET and their role as a traffic manager. In this paper, we propose an intrusion detection system (IDS) for a typical VANET scenario. Our solution approach is underlain on the concepts of learning automata (LA). To the best of our knowledge, no attempts have been made so far to develop any LA-based solution for VANETs. We have designed this system considering the privacy issues involved with the identification of each vehicle. We have evaluated the performance of our proposed solution by conducting a variety of experiments and have found our solution approach to be effective in detecting malicious packets in the system. Specifically, the proposed solution is capable of detecting up to around 90-95% of the malicious packets in the system.

• 出版日期2011-6