Rapid LoRA Aggregation for Wireless Channel Adaptation in Open-Set Radio Frequency Fingerprinting

TL;DR

This paper introduces a lightweight, self-adaptive RFF extraction framework using LoRA for rapid adaptation to new wireless channel conditions, significantly improving authentication accuracy and reducing training time.

Contribution

It presents a novel LoRA-based method that enables fast, environment-specific adaptation of RFF models without full retraining, enhancing open-set wireless authentication.

Findings

Achieved 15% reduction in equal error rate (EER) over non-finetuned baselines.

Reduced training time by 83% compared to full fine-tuning.

Demonstrated effectiveness in dynamic wireless vehicular networks.

Abstract

Radio frequency fingerprints (RFFs) enable secure wireless authentication but struggle in open-set scenarios with unknown devices and varying channels. Existing methods face challenges in generalization and incur high computational costs. We propose a lightweight, self-adaptive RFF extraction framework using Low-Rank Adaptation (LoRA). By pretraining LoRA modules per environment, our method enables fast adaptation to unseen channel conditions without full retraining. During inference, a weighted combination of LoRAs dynamically enhances feature extraction. Experimental results demonstrate a 15% reduction in equal error rate (EER) compared to non-finetuned baselines and an 83% decrease in training time relative to full fine-tuning, using the same training dataset. This approach provides a scalable and efficient solution for open-set RFF authentication in dynamic wireless vehicular networks.