Jammer forensics: Localization in peer to peer networks based on Q-learning

Jamming attacks are a class of network denial of service attacks that can easily be carried out in wireless networks. In order to be able to repair a network in the presence of such attacks, it is desirable to identify the location of jammed nodes and the congested area that is affected by the jammer. In this paper, we propose the design of a Q-learning based attack-localization algorithm that is integrated with the OLSR routing protocol. Our Q-learning attack-localization algorithm is distributed, asynchronous and can identify the location of the jammer in run-time as the attack takes place. We examine the performance of our approach using NS3 network simulations under two different network topologies, and for both naive and intelligent attack scenarios.