Semi-supervised Learning-enabled Two-stage Framework for Cooperative Spectrum Sensing Against SSDF Attack

Cooperative spectrum sensing (CSS) has been considered as a powerful approach to improve the utilization of scarce radio spectrum resources. However, spectrum sensing data falsification (SSDF) can hugely degrade the achievable detection accuracy of the primary user (PU) channel status in cognitive radio (CR) networks and thus requires learning from past CR network environments. Using the supervised learning (SL) method, a large number of labels about the real state of the channel availability need to be acquired. In a practical setting, however, obtaining off-the-shelf label data is a challenging undertaking because it necessitates cooperation among PUs and secondary users (SUs) and increases communication overhead in CR networks. Motivated by this, we solve the issue of label data scarcity in CR networks in this paper, and propose a semi-supervised learning-enabled two-stage framework for CSS against SSDF attack, in which combines the superior performance of semi-supervised support vector machine (S3VM) and the fast convergence of K-means. At last, simulation results demonstrate that S3VM is equipped with a greater detection performance than support vector data description (SVDD), and the same detection performance as support vector machine (SVM), especially it also the robustness and excellent performance using a small amount of labeled data.