This work studies the role of inter-user device-to-device (D2D) cooperation for improving physical-layer secret communication in multi-user downlink systems. It is assumed that there are out-of-band D2D channels, on each of which a selected legitimate user transmits an amplified version of the received downlink signal to other legitimate users. A key technical challenge for designing such systems is that eavesdroppers can overhear downlink as well as D2D cooperation signals. We tackle the problem of jointly optimizing the downlink precoding, artificial noise covariance, and amplification coefficients that maximize the minimum rate. An iterative alternating optimization algorithm is proposed based on the matrix fractional programming. Numerical results confirm the performance gains of the proposed D2D cooperation scheme compared to benchmark secret communication schemes.

翻译：这项工作研究用户间装置到装置(D2D)合作对改进多用户下行链路系统中物理秘密通信的作用,假定有超过频段的D2D频道,每个选定的合法用户都向其他合法用户传送接收的下行链路信号的放大版。设计这种系统的一个关键技术挑战是,偷听器可以偷读下行连接和D2D合作信号。我们处理的问题是,共同优化下行链路预码、人工噪音变异和放大系数,以最大限度地实现最低速率。根据矩阵分数程序,提出了迭代交替优化算法。数字结果证实了提议的D2D合作计划相对于基准秘密通信计划的业绩收益。