VeriPHY: Physical Layer Signal Authentication for Wireless Communication in 5G Environments

2025-08-11

AI Summary

To address vulnerabilities of conventional cryptographic authentication in 5G networks—including susceptibility to protocol-layer attacks and high computational overhead—this paper proposes VeriPHY, a deep learning–based physical-layer authentication (PLA) scheme. VeriPHY innovatively integrates Gaussian mixture models (GMMs) with I/Q-signal steganography to dynamically generate time-varying, device-unique, and covert physical-layer signatures, directly embedded into wireless waveforms. A deep neural network enables end-to-end feature extraction and signature recognition. Experimental results demonstrate authentication accuracy of 93%–100%, low false-positive rates, and inference latency of only 28 ms per authentication. Crucially, VeriPHY maintains >93% detection accuracy even under stealth operation, with signatures refreshed every 20 ms. The scheme thus enables continuous, lightweight, and protocol-attack-resilient device authentication at the physical layer.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Privacy
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Physical layer authentication (PLA) uses inherent characteristics of the communication medium to provide secure and efficient authentication in wireless networks, bypassing the need for traditional cryptographic methods. With advancements in deep learning, PLA has become a widely adopted technique for its accuracy and reliability. In this paper, we introduce VeriPHY, a novel deep learning-based PLA solution for 5G networks, which enables unique device identification by embedding signatures within wireless I/Q transmissions using steganography. VeriPHY continuously generates pseudo-random signatures by sampling from Gaussian Mixture Models whose distribution is carefully varied to ensure signature uniqueness and stealthiness over time, and then embeds the newly generated signatures over I/Q samples transmitted by users to the 5G gNB. Utilizing deep neural networks, VeriPHY identifies and authenticates users based on these embedded signatures. VeriPHY achieves high precision, identifying unique signatures between 93% and 100% with low false positive rates and an inference time of 28 ms when signatures are updated every 20 ms. Additionally, we also demonstrate a stealth generation mode where signatures are generated in a way that makes them virtually indistinguishable from unaltered 5G signals while maintaining over 93% detection accuracy.

Problem

• Develops VeriPHY for secure 5G device authentication
• Embeds stealthy signatures in wireless I/Q transmissions
• Uses deep learning to achieve high authentication accuracy

Innovation

• Deep learning-based physical layer authentication for 5G
• Steganographic embedding of signatures in I/Q transmissions
• Gaussian Mixture Models for pseudo-random signature generation