A Survey of Machine Learning-based Physical-Layer Authentication in Wireless Communications

TL;DR

This paper surveys ML-based physical-layer authentication (PLA) in wireless communications, framing PLA as a scalable, data-driven complement to traditional cryptographic methods. It classifies ML-based PLA into multi-device identification (largely RF fingerprinting) and attack detection (often channel fingerprints), detailing DL architectures (CNNs, RNNs, Transformers, CVNNs), data augmentation, and generative approaches, as well as non-DL techniques (statistical tests, SVM, clustering, GMM, GP, RL). It also inventories open-source RF and channel fingerprint datasets and discusses challenges such as CVNN efficiency, RIS-aided PLA, cross-layer design, interpretability, and the potential of large generative models. The work aims to guide researchers by offering a comprehensive taxonomy, methodological comparisons, and directions toward robust, scalable ML-based PLA systems with practical deployment considerations. Overall, ML-based PLA emerges as a promising framework for secure wireless identity verification in future networks, including IoT, 6G, and beyond.

Abstract

To ensure secure and reliable communication in wireless systems, authenticating the identities of numerous nodes is imperative. Traditional cryptography-based authentication methods suffer from issues such as low compatibility, reliability, and high complexity. Physical-Layer Authentication (PLA) is emerging as a promising complement due to its exploitation of unique properties in wireless environments. Recently, Machine Learning (ML)-based PLA has gained attention for its intelligence, adaptability, universality, and scalability compared to non-ML approaches. However, a comprehensive overview of state-of-the-art ML-based PLA and its foundational aspects is lacking. This paper presents a comprehensive survey of characteristics and technologies that can be used in the ML-based PLA. We categorize existing ML-based PLA schemes into two main types: multi-device identification and attack detection schemes. In deep learning-based multi-device identification schemes, Deep Neural Networks are employed to train models, avoiding complex processing and expert feature transformation. Deep learning-based multi-device identification schemes are further subdivided, with schemes based on Convolutional Neural Networks being extensively researched. In ML-based attack detection schemes, receivers utilize intelligent ML techniques to set detection thresholds automatically, eliminating the need for manual calculation or knowledge of channel models. ML-based attack detection schemes are categorized into three sub-types: Supervised Learning, Unsupervised Learning, and Reinforcement Learning. Additionally, we summarize open-source datasets used for PLA, encompassing Radio Frequency fingerprints and channel fingerprints. Finally, this paper outlines future research directions to guide researchers in related fields.

Figures (9)

• Figure 1: Organization of the paper.
• Figure 3: Organization of Section II.
• Figure 4: Illustration of the non-DL-based and DL-based multi-device identification methods.
• Figure 6: Illustration of the non-ML-based and ML-based attack detection methods.
• Figure 8: Organization of Section III.