Radio Frequency Fingerprinting Identification (RFFI) is a lightweight authentication method at the physical layer for LoRa IoT devices that avoids cryptographic overhead. However, current deep learning pipelines for RFFI face a robustness gap in that their identification accuracy can decline in time-varying multipath environments caused by real-world mobility, especially in non-line-of-sight (NLOS) settings. Earlier mitigations rely on data augmentation or implicit channel normalization, yet the resulting features often remain dominated by the deterministic LoRa chirp, which can overshadow device-specific hardware signatures. We proposed a physics-informed residual (PIR) framework that incorporates domain knowledge directly into the extraction of features, thereby enhancing the detection of these hardware imperfections. PIR aligns the received preamble and, in the Channel Independent Spectrogram (CIS) domain, subtracts an equally processed ideal LoRa reference. This operation emphasizes residual patterns linked to transmitter hardware impairments and improves numerical stability. We assess the method on a public dataset of commercial LoRa devices, using a homogeneous set of 45 SX1276-based transceivers split across training, open-set enrollment, and rogue device evaluation. The results indicate more robust performance in most scenarios while maintaining strong open-set rogue detection with Area Under the Curve (AUC) greater than 0.99. These findings suggest that physics-informed representation design can enhance the reliability of LoRa RFFI under dynamic deployment conditions.
- Open Access
- Article
Enhancing Channel Robustness in LoRa Radio Frequency Fingerprinting through a Physics-Informed Residual Spectrogram †
- Elisée Toe 1,*,
- Laurent Ferrier 1,2,
- Fehmi Jaafar 1
Author Information
Received: 21 Jul 2026 | Revised: 24 Jul 2026 | Accepted: 31 Jul 2026 | Published: 10 Aug 2026
Abstract
Keywords
LoRa | radio frequency fingerprinting | physical-layer authentication | physics-informed learning | channel robustness
References
- 1.
Milarokostas, C.; Tsolkas, D.; Passas, N.; et al. A Comprehensive Study on LPWANs with a Focus on the Potential of LoRa/LoRaWAN Systems. IEEE Commun. Surv. Tutor. 2023, 25, 825–867.
- 2.
Toe, E.; Jaafar, F.; Ferrier, L. Securing LoRaWAN in the AIoT Era: A Systematic Mapping Study and an MITRE-Based Threat Matrix. IEEE Internet Things J. 2026, 13, 3827–3849.
- 3.
Zhang, T.; Ren, P.; Xu, D.; et al. DFSNet: Deep Fractional Scattering Network for LoRa Fingerprinting. In Proceedings of the GLOBECOM 2022—2022 IEEE Global Communications Conference, Rio de Janeiro, Brazil, 4–8 December 2022; pp. 4897–4902.
- 4.
Nair, M.; Dang, S.; Beach, M.A. IoT Device Authentication Using Self-Organizing Feature Map Data Sets. IEEE Commun. Mag. 2023, 61, 162–168.
- 5.
Li, B.; Cetin, E. Design and Evaluation of a Graphical Deep Learning Approach for RF Fingerprinting. IEEE Sens. J. 2021, 21, 19462–19468.
- 6.
Hamdaoui, B.; Elmaghbub, A. Deep-Learning-Based Device Fingerprinting for Increased LoRa-IoT Security: Sensitivity to Network Deployment Changes. IEEE Netw. 2022, 36, 204–210.
- 7.
Huang, D.; Al-Hourani, A. Physical Layer Spoof Detection and Authentication for IoT Devices Using Deep Learning Methods. IEEE Trans. Mach. Learn. Commun. Netw. 2024, 2, 841–854.
- 8.
Zhang, J.; Ardizzon, F.; Piana, M.; et al. Physical Layer-Based Device Fingerprinting for Wireless Security: From Theory to Practice. IEEE Trans. Inf. Forensics Secur. 2025, 20, 5296–5325.
- 9.
Elmaghbub, A.; Hamdaoui, B. Distinguishable IQ Feature Representation for Domain-Adaptation Learning of WiFi Device Fingerprints. IEEE Trans. Mach. Learn. Commun. Netw. 2024, 2, 1404–1423.
- 10.
Baldini, G.; Bonavitacola, F. LoRa Radio Frequency Fingerprinting with Residual of Variational Mode Decomposition and Hybrid Machine-Learning/Deep-Learning Optimization. Electronics 2024, 13, 1925.
- 11.
Huan, X.; Wu, C.; Lei, Y.; et al. LLRF: Towards Long-Term LoRa Radio Frequency Fingerprint Identification Based on Transfer Learning. IEEE Trans. Veh. Technol. 2025, 74, 19921–19926.
- 12.
Al-Shawabka, A.; Pietraski, P.; Pattar, S.B.; et al. SignCRF: Scalable Channel-Agnostic Data-Driven Radio Authentication System. IEEE Trans. Mobile Comput. 2025, 24, 9383–9394.
- 13.
Xie, R.; Xu, W.; Chen, Y.; et al. A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authentication. IEEE Trans. Inf. Forensics Secur. 2021, 16, 4435–4450.
- 14.
Shen, G.; Zhang, J.; Marshall, A.; et al. Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa. IEEE Trans. Inf. Forensics Secur. 2022, 17, 774–787.
- 15.
Al-Shawabka, A.; Pietraski, P.; Pattar, S.B.; et al. DeepLoRa: Fingerprinting LoRa Devices at Scale Through Deep Learning and Data Augmentation. In Proceedings of the Twenty-Second International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing; ACM: Shanghai, China, 26–29 July 2021; pp. 251–260.
- 16.
Ahmed, A.; Quoitin, B.; Gros, A.; et al. A Comprehensive Survey on Deep Learning-Based LoRa Radio Frequency Fingerprinting Identification. Sensors 2024, 24, 4411.
- 17.
Elmaghbub, A.; Hamdaoui, B. LoRa Device Fingerprinting in the Wild: Disclosing RF Data-Driven Fingerprint Sensitivity to Deployment Variability. IEEE Access 2021, 9, 142893–142909.
- 18.
Zhou, X.; Hu, A.; Li, G.; et al. A Robust Radio-Frequency Fingerprint Extraction Scheme for Practical Device Recognition. IEEE Internet Things J. 2021, 8, 11276–11289.
- 19.
Gaskin, J.; Hamdaoui, B.; Wong, W.K. Tweak: Towards Portable Deep Learning Models for Domain-Agnostic LoRa Device Authentication. In Proceedings of the 2022 IEEE Conference on Communications and Network Security (CNS), Austin, TX, USA, 3–5 October 2022; pp. 1–9.
- 20.
Jian, T.; Rendon, B.C.; Ojuba, E.; et al. Deep Learning for RF Fingerprinting: A Massive Experimental Study. IEEE Internet Things Mag. 2020, 3, 50–57.
- 21.
Shen, G.; Zhang, J.; Marshall, A.; et al. Radio Frequency Fingerprint Identification for LoRa Using Spectrogram and CNN. In Proceedings of the IEEE INFOCOM 2021—IEEE Conference on Computer Communications, Vancouver, BC, Canada, 10–13 May 2021; pp. 1–10.
- 22.
Shen, G.; Zhang, J.; Marshall, A.; et al. Toward Length-Versatile and Noise-Robust Radio Frequency Fingerprint Identification. IEEE Trans. Inf. Forensics Secur. 2023, 18, 2355–2367.
- 23.
Pan, R.; Chen, H.; Shen, G.; et al. Residual Channel Boosts Contrastive Learning for Radio Frequency Fingerprint Identification. IEEE Wirel. Commun. Lett. 2025, 14, 1728–1732.
- 24.
Maleki, A.; Nguyen, H.H.; Bedeer, E.; et al. A Tutorial on Chirp Spread Spectrum Modulation for LoRaWAN: Basics and Key Advances. IEEE Open J. Commun. Soc. 2024, 5, 4578–4612.
- 25.
Elmaghbub, A.; Hamdaoui, B. Comprehensive RF Dataset Collection and Release: A Deep Learning-Based Device Fingerprinting Use Case. In Proceedings of the 2021 IEEE Globecom Workshops (GC Wkshps), Madrid, Spain, 7–11 December 2021; pp. 1–7.
- 26.
Restuccia, F.; D’Oro, S.; Al-Shawabka, A.; et al. DeepRadioID: Real-Time Channel-Resilient Optimization of Deep Learning-Based Radio Fingerprinting Algorithms. In Proceedings of the Twentieth ACM International Symposium on Mobile Ad Hoc Networking and Computing, Catania, Italy, 2–5 July 2019; pp. 51–60.
- 27.
Chen, Z.; Peng, L.; Hu, A.; et al. Generative Adversarial Network-Based Rogue Device Identification Using Differential Constellation Trace Figure. EURASIP J. Wireless Commun. Netw. 2021, 2021, 72.
- 28.
Shen, G.; Zhang, J.; Marshall, A. LoRa RFFI dataset. Available online: https://ieee-dataport.org/open-access/lorarffidataset (accessed on 6 September 2025).
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com