Efficient utilization of licensed spectrum in the cognitive radio network is challenging due to lack of coordination among the Secondary Users (SUs). Distributed algorithms proposed in the literature aim to maximize the network throughput by ensuring orthogonal channel allocation for the SUs. However, these algorithms work under the assumption that all the SUs faithfully follow the algorithms which may not always hold due to the decentralized nature of the network. In this paper, we study distributed algorithms that are robust against malicious behavior (jamming attack). We consider both the cases of jammers launching coordinated and uncoordinated attacks. In the coordinated attack, the jammers select non-overlapping channels to attack in each time slot and can significantly increase the number of collisions for SUs. We setup the problem in each scenario as a multi-player bandit and develop algorithms. The analysis shows that when the SUs faithfully implement proposed algorithms, the regret is constant with high probability. We validate our claims through exhaustive synthetic experiments and also through a realistic USRP based experiment.

Efficient utilization of licensed spectrum in the cognitive radio network is challenging due to lack of coordination among the Secondary Users (SUs). Distributed algorithms proposed in the literature aim to maximize the network throughput by ensuring orthogonal channel allocation for the SUs. However, these algorithms work under the assumption that all the SUs faithfully follow the algorithms which may not always hold due to the decentralized nature of the network. Moreover, they are vulnerable to Denial of Service attacks. In this paper, we study distributed algorithms that are robust against malicious behavior (jamming attack). We consider jammers launching coordinated attack where they select non-overlapping channels in each time slot and can lead to significantly higher number of collisions for SUs than uncoordinated attack. We setup the problem as a multiplayer bandit and develop distributed learning algorithms. The analysis shows that when the SUs faithfully implement proposed algorithms, the regret is constant with high probability. We validate our claims through exhaustive synthetic experiments and also through a realistic USRP based experiments.