Research Article
Biometric Authentication in Galvanic Coupling Communications: A Physical Layer Approach for Secure Wearable Medical Systems
@INPROCEEDINGS{10.1007/978-3-032-38657-1_9, author={Stefano Caputo and Anna Vizziello and Antonio Coviello and Maurizio Magarini and Giacomo Borghini and Pietro Savazzi and Sara Jayousi and Lorenzo Mucchi}, title={Biometric Authentication in Galvanic Coupling Communications: A Physical Layer Approach for Secure Wearable Medical Systems}, proceedings={Body Area Networks. 20th EAI International Conference, BodyNets 2025, Okayama, Japan, December 2--4, 2025, Proceedings}, proceedings_a={BODYNETS}, year={2026}, month={10}, keywords={Physical Layer Authentication Wireless Body Area Network Galvanic Coupling (GC) On-Body Communications Long Short-Term Memory Neural Network (LSTM) Deep Learning signal classification}, doi={10.1007/978-3-032-38657-1_9} }- Stefano Caputo
Anna Vizziello
Antonio Coviello
Maurizio Magarini
Giacomo Borghini
Pietro Savazzi
Sara Jayousi
Lorenzo Mucchi
Year: 2026
Biometric Authentication in Galvanic Coupling Communications: A Physical Layer Approach for Secure Wearable Medical Systems
BODYNETS
Springer
DOI: 10.1007/978-3-032-38657-1_9
Abstract
This paper presents a biometric authentication framework based on Galvanic Coupling (GC) signals for secure communication in Wireless Body Area Networks (WBANs). Unlike traditional biometric systems that rely on handcrafted features, our approach leverages a Long Short-Term Memory (LSTM) neural network to classify raw GC signals directly, exploiting the subject-specific characteristics of the propagation channel. The system is designed for on-body configurations and integrates a lightweight authentication protocol that operates at the physical layer. Experimental results demonstrate the effectiveness of the proposed method in mitigating both over-the-air and direct contact attacks, achieving high classification accuracy and robustness through confidence-based rejection mechanisms. The solution is optimized for low-resource environments, making it suitable for real-time medical applications.