标题： 生成式人工智能赋能的无线通信用于稳健的低空经济网络 显示英文标题

标题： Generative AI-enabled Wireless Communications for Robust Low-Altitude Economy Networking

摘要： 低空经济网络（LAENets）已成为社会活动的重要推动者，提供低空服务，如包裹、杂货和医疗用品的运输。 由于其控制机制和不断变化的操作因素，LAENets本质上比传统地面网络更复杂，并且更容易受到安全威胁。 随着LAENet应用的持续扩展，这些系统的鲁棒性变得至关重要。 在本文中，我们提出了一种生成式人工智能（GenAI）优化框架，以解决LAENets中的鲁棒性挑战。 我们对LAENets的鲁棒性需求进行了系统分析，并从无线物理层的角度全面回顾了鲁棒服务质量（QoS）指标。 然后，我们研究了现有的基于GenAI的鲁棒性增强方法。 这导致我们提出了一个基于扩散的优化框架，该框架具有专家混合（MoE）-transformer执行器网络。 在鲁棒波束成形的案例研究中，所提出的框架通过在不确定性下优化波束成形展示了其有效性，在最坏情况下的可实现保密速率上，超过了四个学习基线，提高了超过15%。 这些发现突显了GenAI在增强LAENet鲁棒性方面的巨大潜力。 显示英文摘要

摘要： Low-Altitude Economy Networks (LAENets) have emerged as significant enablers of social activities, offering low-altitude services such as the transportation of packages, groceries, and medical supplies. Owing to their control mechanisms and ever-changing operational factors, LAENets are inherently more complex and vulnerable to security threats than traditional terrestrial networks. As applications of LAENet continue to expand, the robustness of these systems becomes crucial. In this paper, we propose a generative artificial intelligence (GenAI) optimization framework that tackles robustness challenges in LAENets. We conduct a systematic analysis of robustness requirements for LAENets, complemented by a comprehensive review of robust Quality of Service (QoS) metrics from the wireless physical layer perspective. We then investigate existing GenAI-enabled approaches for robustness enhancement. This leads to our proposal of a novel diffusion-based optimization framework with a Mixture of Experts (MoE)-transformer actor network. In the robust beamforming case study, the proposed framework demonstrates its effectiveness by optimizing beamforming under uncertainties, achieving a more than 15% increase over four learning baselines in the worst-case achievable secrecy rate. These findings highlight the significant potential of GenAI in strengthening LAENet robustness.