Detection of SSDF Attack Using SVDD Algorithm in Cognitive Radio Networks

In this paper, a new robust algorithm is proposed for spectrum sensing in cognitive radio networks. The goal of spectrum sensing is to identify holes. Malicious nodes are degraded the performance of spectrum sensing. To mitigate spectrum sensing data falsification attack, we employ support vector data description in sensing procedure. The SVDD algorithm distinguishes malicious nodes from trusted ones and omits them from decision phase. In other words, the proposed algorithm omits outliers from decision phase. It tries to construct the boundary around the target data by enclosing the target data within a minimum hyper-sphere. Inspired by the support vector machine the SVDD decision boundary is described by a few target objects, known as support vectors. Then the algorithm votes between trusted nodes to decide whether the spectrum is empty. The performance of the proposed algorithm is evaluated by computer simulations.