Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training

2025-10-10

AI Summary

Radio frequency fingerprint identification (RFFI) suffers from feature shift induced by hardware variations across receivers, severely degrading cross-receiver generalization. To address this, we propose a receiver-robust RFFI framework that—novelty—the first to integrate adversarial training with style transfer, explicitly disentangling transmitter identity features from receiver-specific biases to construct domain-invariant representations. Our method employs a deep neural network architecture that jointly performs feature disentanglement, domain adaptation, and receiver-aware adversarial optimization, enabling clean extraction of transmitter-specific hardware fingerprints. Evaluated on a multi-receiver real-world dataset, our approach achieves an average identification accuracy improvement of up to 10% over state-of-the-art methods, significantly mitigating performance degradation caused by receiver replacement. This work provides a scalable, robust solution for practical RFFI deployment.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

Abstract

Radio frequency fingerprint identification (RFFI) is a critical technique for wireless network security, leveraging intrinsic hardware-level imperfections introduced during device manufacturing to enable precise transmitter identification. While deep neural networks have shown remarkable capability in extracting discriminative features, their real-world deployment is hindered by receiver-induced variability. In practice, RF fingerprint signals comprise transmitter-specific features as well as channel distortions and receiver-induced biases. Although channel equalization can mitigate channel noise, receiver-induced feature shifts remain largely unaddressed, causing the RFFI models to overfit to receiver-specific patterns. This limitation is particularly problematic when training and evaluation share the same receiver, as replacing the receiver in deployment can cause substantial performance degradation. To tackle this challenge, we propose an RFFI framework robust to cross-receiver variability, integrating adversarial training and style transfer to explicitly disentangle transmitter and receiver features. By enforcing domain-invariant representation learning, our method isolates genuine hardware signatures from receiver artifacts, ensuring robustness against receiver changes. Extensive experiments on multi-receiver datasets demonstrate that our approach consistently outperforms state-of-the-art baselines, achieving up to a 10% improvement in average accuracy across diverse receiver settings.

Problem

• Addressing receiver-induced feature shifts in RF fingerprint identification
• Disentangling transmitter and receiver features via adversarial training
• Ensuring cross-receiver generalization for wireless security applications

Innovation

• Disentangles transmitter and receiver features
• Uses adversarial training for domain-invariant representations
• Applies style transfer to isolate hardware signatures