Distributed adaptive authentication improves 6G aerial network security
Adaptive Distributed Physical-Layer Authentication and Attack Detection in 6G Non-Terrestrial Networks via Causal Meta-Learning
Artificial IntelligenceCryptography and SecurityMachine Learning
Summary
Authenticating devices in 6G satellite and aerial networks is hard because signals can shift and change quickly. The authors propose a system that uses multiple signal features and smart learning techniques to quickly detect attacks even when conditions change. Their method works across different environments and keeps communication networks safer by verifying who is really sending messages. This approach reduces the data needed to confirm identities while improving accuracy.
What this means in practice
- •For wireless network engineers: Enhance security of aerial and satellite communication by adapting device authentication to varying signal conditions with few samples per new environment.
- •For internet of things integrators: Implement efficient multi-feature device identity verification in airborne IoT deployments to detect unauthorized devices under shifting channel conditions.
Authors
Parsa Rajabi, Mohammad Reza Abedi, Nader Mokari, Paeiz Azmi, Halim Yanikomeroglu
Abstract
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.