Reliable and secure communication is an important aspect of modern fiber optic communication. In this work we consider a multi-mode fiber (MMF) channel wiretapped by an eavesdropper. We assume the transmitter knows the legitimate channel, but statistical knowledge of the eavesdropper's channel only. We propose a transmission scheme with artificial noise (AN) for such a channel. In particular, we formulate the corresponding optimization problem which aims to maximize the average secrecy rate and develop an algorithm to solve it. We apply this algorithm to actual measured MMF channels. As real fiber measurements show, for a 55 mode MMF we can achieve positive average secrecy rates with the proper use of AN. Furthermore, the gain compared to standard precoding and power allocation schemes is illustrated.

翻译：可靠和安全的通信是现代光纤通信的一个重要方面。 在这项工作中,我们考虑的是由窃听器窃听器窃听的多模式纤维(MMF)频道。 我们假设发射器知道合法的频道,但只知道窃听器频道的统计知识。 我们为这样一个频道提出了一个带有人工噪音的传输计划。 特别是, 我们提出相应的优化问题, 目的是最大限度地提高平均保密率, 并开发一种算法来解决这个问题。 我们把这个算法应用到实际测量的MMF频道。 正如真实的纤维测量显示的那样, 对于55种模式的MMMF, 我们可以通过AN的适当使用实现平均保密率。 此外, 与标准的预编码和权力分配计划相比, 收益也得到了说明。