Practical Physical Layer Authentication for Mobile Scenarios Using a Synthetic Dataset Enhanced Deep Learning Approach

2025-08-28

AI Summary

In mobile IoT scenarios, physical-layer device authentication suffers from vulnerabilities induced by wireless broadcast characteristics and dynamic channel variations, heavy reliance on empirical measurements, and poor generalization. To address these challenges, this paper proposes a synthetic-data-augmented Siamese-CNN authentication framework. We innovatively generate high-fidelity Channel State Information (CSI) synthetic data using the WLAN TGn channel model, design a convolutional Siamese network that jointly exploits spatiotemporal correlations, and introduce a joint autocorrelation–distance-correlation analysis mechanism. Evaluated under the IEEE 802.11n standard via simulation and validated on a real-world WiFi testbed, our method achieves an AUC of 0.982—improving upon a fully connected Siamese baseline by 0.03 and over conventional correlation-based methods by 0.06. It significantly reduces dependence on measured data while enhancing robustness and generalization under dynamic channel conditions.

Technology Category

• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Computer Vision: Motion & Tracking
• Humans and AI: Interaction Techniques and Devices

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The Internet of Things (IoT) is ubiquitous thanks to the rapid development of wireless technologies. However, the broadcast nature of wireless transmissions results in great vulnerability to device authentication. Physical layer authentication emerges as a promising approach by exploiting the unique channel characteristics. However, a practical scheme applicable to dynamic channel variations is still missing. In this paper, we proposed a deep learning-based physical layer channel state information (CSI) authentication for mobile scenarios and carried out comprehensive simulation and experimental evaluation using IEEE 802.11n. Specifically, a synthetic training dataset was generated based on the WLAN TGn channel model and the autocorrelation and the distance correlation of the channel, which can significantly reduce the overhead of manually collecting experimental datasets. A convolutional neural network (CNN)-based Siamese network was exploited to learn the temporal and spatial correlation between the CSI pair and output a score to measure their similarity. We adopted a synergistic methodology involving both simulation and experimental evaluation. The experimental testbed consisted of WiFi IoT development kits and a few typical scenarios were specifically considered. Both simulation and experimental evaluation demonstrated excellent generalization performance of our proposed deep learning-based approach and excellent authentication performance. Demonstrated by our practical measurement results, our proposed scheme improved the area under the curve (AUC) by 0.03 compared to the fully connected network-based (FCN-based) Siamese model and by 0.06 compared to the correlation-based benchmark algorithm.

Problem

• Enhancing mobile device authentication using deep learning
• Reducing dataset collection overhead with synthetic data
• Improving authentication performance in dynamic wireless channels

Innovation

• Deep learning-based CSI authentication for mobile scenarios
• Synthetic dataset generation using WLAN TGn channel model
• CNN-based Siamese network for temporal-spatial correlation learning