Enhancing Physical Layer Authentication in Mobile WiFi Environments Using Sliding Window and Deep Learning

The convenience of wireless communication has led to its widespread adoption across various application scenarios. However, existing Physical Layer Authentication (PLA) schemes still have limitations in terms of adaptability. This paper introduces a novel method based on key-less channel-based authentication framework designed to enhance PLA performance under different mobility patterns. Our method combines the sliding window with a model based on a siamese neural network, enabling a fully connected neural network classifier to effectively distinguish between legitimate transmitters and potential attackers, achieving an accuracy of 97.91%. Experiments conducted in various environments demonstrate the robustness and high performance of the proposed method, making it well-suited for deployment in time-varying environments with high-security demands and resource constraints.

I. Introduction

Wireless communication technology has significantly enhanced the flexibility and mobility of communication devices. However, cryptographic methods implemented at the upper layers of network security reveal several limitations when ensuring secure wireless communication. In contrast, Physical Layer Authentication (PLA) has emerged as a promising technology that can provide enhanced security [1], [2]. Generally, PLA methods can be categorized into two types based on whether a key is used for authentication: key-based and key-less. One of the earliest key-less channel-based authentication schemes was proposed by Xiao et al., who established the relevant framework in their work [3]. Later, they extended this approach to time-variant wireless channels in their work [4]. This research sparked widespread interest in key-less PLA methods. Baracca et al. aimed to provide practical authentication solutions for various modern communication systems using PLA [5]. Xie et al. successfully addressed privacy issues in Non-Orthogonal Multiple Access (NOMA) systems using channel reciprocity-based PLA, significantly improving privacy protection [6]. However, the robustness and security of CSI difference-based PLA are severely affected by the inherent characteristics of the channel [7]. The dynamic nature of mobile communication devices, combined with fading effects within wireless channels, leads to rapid fluctuations and instability of physical layer attributes [8]. Moreover, in densely built urban environments, the rapid spatial decorrelation of wireless multipath channels can result in entirely different channel responses even with minor movements of mobile devices. These factors substantially limit the performance of existing CSI difference-based PLA schemes. Therefore, there is an urgent need to enhance the authentication performance of PLA schemes under various mobility patterns, which holds significant practical value [9].