Spectrum sharing is increasingly vital in 6G wireless communication,
facilitating dynamic access to unused spectrum holes. Recently, there has been
a significant shift towards employing machine learning (ML) techniques for
sensing spectrum holes. In this context, federated learning (FL)-enabled
spectrum sensing technology has garnered wide attention, allowing for the
construction of an aggregated ML model without disclosing the private spectrum
sensing information of wireless user devices. However, the integrity of
collaborative training and the privacy of spectrum information from local users
have remained largely unexplored. This article first examines the latest
developments in FL-enabled spectrum sharing for prospective 6G scenarios. It
then identifies practical attack vectors in 6G to illustrate potential
AI-powered security and privacy threats in these contexts. Finally, the study
outlines future directions, including practical defense challenges and
guidelines.

6G 无线通信中的频谱共享越来越重要，机器学习技术的应用在感知频谱空洞方面发生了显著变化，通过联邦学习实现的频谱感知技术引起了广泛关注，但协作训练的完整性和本地用户频谱信息的隐私安全问题仍然未被充分探索。本文首先研究了适用于 6G 场景的联邦学习优势频谱共享的最新发展，并指出了其中的安全和隐私威胁。最后，本研究提出了未来的发展方向，包括实际防御挑战和指导。

6G 联邦学习动态频谱共享的安全与隐私

Security and Privacy of 6G Federated Learning-enabled Dynamic Spectrum  Sharing

Reconfigurable intelligent surfaces (RISs) are considered as potential
technologies for the upcoming sixth-generation (6G) wireless communication
system. Various benefits brought by deploying one or multiple RISs include
increased spectrum and energy efficiency, enhanced connectivity, extended
communication coverage, reduced complexity at transceivers, and even improved
localization accuracy. However, to unleash their full potential, fundamentals
related to RISs, ranging from physical-layer (PHY) modelling to RIS phase
control, need to be addressed thoroughly. In this paper, we provide an overview
of some timely research problems related to the RIS technology, i.e., PHY
modelling (including also physics), channel estimation, potential RIS
architectures, and RIS phase control (via both model-based and data-driven
approaches), along with recent numerical results. We envision that more efforts
will be devoted towards intelligent wireless environments, enabled by RISs.

本文综述了与可重构智能表面（RIS）技术相关的一些及时研究问题，包括物理层建模，信道估计，潜在的 RIS 体系结构和 RIS 相位控制，并提供了最近的数值结果。