基于联合对角化的抗人工噪声干扰算法  

Anti-interference of Artificial Noise Aided Secure Communications Based on JADE

作　　者：李欣欣[1] 蔡晓霞[1] 朱文丽[1] LI Xinxin CAI Xiaoxia ZHU Wenli(Electronic Engineering Institute of PLA, Hefei 230037, Chin)

机构地区：[1]解放军电子工程学院,安徽合肥230037

出　　处：《探测与控制学报》2017年第2期66-71,共6页Journal of Detection & Control

基　　金：国家自然科学基金项目资助(61171170)

摘　　要：针对无线通信中通信双方采用人工噪声物理层安全算法通信时,窃听方因受到人工噪声干扰无法有效窃听的问题,提出基于联合对角化的抗人工噪声干扰算法。该算法首先对接收信号进行信号源数目预估计,并对其进行预处理;其次通过构造四阶累积量矩阵,并对其进行特征值分解以估计混合矩阵,进而将通信信号、人工噪声与环境噪声信号分离,最终提取出窃听信道中较弱的通信信号以达到抗噪声干扰的目的。理论分析和仿真结果表明,该算法在窃听方受到合法通信方发射的人工噪声干扰时,能够有效分离出目标信号,且在一定信噪比条件下与传统盲源分离方法相比分离效果更佳。The broadcast nature of wireless channels leads to the developments and applications of physical layer security techniques. The artificial noise （AN） aided technique is proposed to interfere with the eavesdropper for secure communications？ which is a great challenge to the eavesdropper. A suppression method named Joint Approximate Diagonalization of Eigen-matrices （JADE） , which is based on blind source separation （BSS） algorithm, was presented under this circumstance. Firstly, the numbers of source signals was pre-esti-mated and receiving signals were pre-treated. By introducing fourth-order cumulant matrix for the estimation of mixture matrix. Simulation results demonstrated that JADE was feasible under certain circumstances, which helped the eavesdropper to defeat the AN aided secure communications effectively. Furthermore, the proposed algorithm performs better than conventional BSS methods under the same circumstances.

关 键 词：物理层安全 人工噪声 盲源分离 联合对角化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]