An Online Learning Approach for Cooperator Selection in CSS Under SSDF Attack

Cooperative spectrum sensing (CSS) can greatly improve sensing accuracy by combining the individual sensing results. However, it also faces spectrum sensing data falsification (SSDF) attack which degrades the cooperative sensing performance in practice. To deal with SSDF attack and reduce total energy consumption, it is recommended to select reliable secondary users (SUs) and SUs which have the best detection performance for cooperation. In this letter, an online learning based user selection algorithm is proposed according to the approximate ground truth about the licensed channel state, which addresses the practical problem that different users have different sensing capability and may launch SSDF attacks. In addition, the cooperator's trust degree is updated in the online learning process. Simulation results indicate that the proposed SUs selection algorithm can quickly converge to a stable state in terms of collision probability and spectrum waste probability under highly unreliable conditions.