AI 中文总结
研究全双工基站系统中安全上行链路传输，通过联合优化多参数最大化安全能效。提出基于混合梯度的元学习框架，闭式解更新部分参数，神经元优化器更新其余耦合变量，该设计性能优于基准和多种基线。
AI 中文摘要
安全能效（SEE）已成为下一代无线网络的关键性能指标，必须同时保证能源可持续性和信息安全。本文研究了在存在多个协作无源窃听者的情况下，配备移动天线（MA）并由可移动元件可重构智能表面（ME-RIS）辅助的全双工（FD）基站（BS）系统中的安全上行链路传输。目标是通过联合优化用户发射功率、基站接收预编码器、人工噪声（AN）发射功率和波束成形、RIS相移以及基站天线和RIS元件的二维位置来最大化SEE。由于分数SEE目标、耦合保密率表达式、残余自干扰（SI）、单位模RIS相移约束、移动位置约束、元件间距要求以及信道对移动天线和RIS元件位置的非线性依赖性，所产生的优化问题高度非凸。为应对这些挑战，我们提出了一种基于混合梯度的元学习（H-GML）框架。在所提出的方法中，基站接收预编码器和AN方向使用从广义瑞利商公式导出的闭式解进行更新，而其余耦合变量由神经元优化器更新，该优化器直接从SEE优化目标学习基于梯度的更新方向，无需离线标记训练数据。仿真结果表明，所提出的H-GML设计比AO基准具有更好的性能，并且明显优于固定几何、随机RIS、无AN和无Eve知识基线。
英文摘要
Secure energy efficiency (SEE) has emerged as a key performance metric for next-generation wireless networks, where energy sustainability and information security must be jointly guaranteed. This paper investigates secure uplink transmission in a full-duplex (FD) base station (BS) system equipped with movable antennas (MAs) and assisted by a movable-element reconfigurable intelligent surface (ME-RIS) in the presence of multiple cooperative passive eavesdroppers. The objective is to maximize SEE by jointly optimizing the users' transmit powers, BS receive postcoders, artificial noise (AN) transmit power and beamforming, RIS phase shifts, and the two-dimensional positions of both the BS antennas and RIS elements. The resulting optimization problem is highly nonconvex due to the fractional SEE objective, coupled secrecy-rate expressions, residual self-interference (SI), unit-modulus RIS phase-shift constraints, movable-position constraints, inter-element spacing requirements, and the nonlinear dependence of the channels on the movable antenna and RIS-element positions. To address these challenges, we propose a hybrid gradient-based meta-learning (H-GML) framework. In the proposed method, the BS receive postcoders and AN direction are updated using closed-form solutions derived from generalized Rayleigh quotient formulations, while the remaining coupled variables are updated by neural meta-optimizers that learn gradient-based update directions directly from the SEE optimization objective without requiring offline labeled training data. Simulation results show that the proposed H-GML design achieves better performance than the AO benchmark and significantly outperforms fixed-geometry, random RIS, no-AN, and no-Eve-knowledge baselines.
