发表机构
Tarbiat Modares University; Carleton University（塔比亚特·莫达雷斯大学; 卡尔顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对6G非地面网络中物理层认证因环境分布偏移而性能下降的问题，提出基于因果元学习的分布式自适应框架SAFA-MZ，融合多特征指纹与因果一致性，实现快速适应并降低开销，在仿真中准确率达92%。
AI 中文摘要
非地面网络（NTN）中的物理层认证（PLA）面临严重的多普勒频移、长时延和快速信道变化等挑战，这些因素导致分布偏移并降低传统学习方法的性能。现有的PLA方案通常依赖单一特征或对未见环境泛化能力差。本文提出了一种用于多区域网络认证的安全自适应框架（SAFA-MZ），这是一种用于NTN中分布式PLA（DPLA）的因果元学习框架。首先，我们设计了一种结合空间、角度、合并器、子空间和多普勒-延迟特征的多特征指纹。该指纹是自适应和分布式的，因为它融合了来自多个空中节点的异构物理层特征和测量值。其次，我们构建了一个结构因果模型（SCM）来捕捉设计选择、环境因素、提取特征和认证结果之间的关系。第三，我们开发了一种结合不变风险最小化（IRM）和因果一致性正则化的模型无关元学习（MAML）策略，以便在少量标记样本下快速适应未见过的NTN环境。第四，我们提出了一种两阶段认证方案，该方案执行本地识别，并仅在需要时激活基于图注意力（GAT）网络的到达时间差（TDOA）定位，从而降低回程开销。仿真结果表明，SAFA-MZ在不同环境下实现了92%的准确率和96%的AUC，优于集中式深度学习和单特征基线。
英文摘要
Physical-layer authentication (PLA) in non-terrestrial networks (NTNs) is challenged by severe Doppler shifts, long delays, and fast channel variations, which cause distribution shifts and degrade conventional learning methods. Existing PLA schemes often rely on single features or generalize poorly to unseen environments. This paper proposes a secure adaptive framework for authentication in multi-zone networks (SAFA-MZ), a causal meta-learning framework for distributed PLA (DPLA) in NTNs. First, we design a multi-feature fingerprint that combines spatial, angular, combiner, subspace, and Doppler-delay features. The fingerprint is adaptive and distributed, as it fuses heterogeneous physical-layer features and measurements from multiple aerial nodes. Second, we formulate a structural causal model (SCM) to capture the relations among design choices, environmental factors, extracted features, and authentication outcomes. Third, we develop a model-agnostic meta-learning (MAML) strategy with invariant risk minimization (IRM) and causal consistency regularization for fast adaptation to unseen NTN environments with few labeled samples. Fourth, we propose a two-stage authentication scheme that performs local recognition and activates time-difference-of-arrival (TDOA) localization with a graph attention (GAT) network only when needed, which reduces backhaul overhead. Simulations show that SAFA-MZ achieves 92% accuracy and 96% AUC, outperforming centralized deep learning and single-feature baselines across diverse environments.
