arXiv:2510.09405v2 Announce Type: replace 
Abstract: Radio frequency fingerprint identification (RFFI) is a key technique for wireless network security, leveraging intrinsic hardware imperfections to enable transmitter identification. Although deep neural networks are effective at extracting discriminative RF features, their performance is significantly affected by receiver-induced variability in practical deployments. In real-world scenarios, RF signals inherently entangle transmitter-specific characteristics with receiver-dependent distortions, leading models to capture receiver-related patterns when training and evaluation are conducted on the same device. Consequently, replacing the receiver during deployment often results in notable performance degradation. To address this issue, we propose a cross-receiver robust RFFI framework that explicitly disentangles transmitter-specific and receiver-specific representations. The proposed method integrates adversarial domain alignment with receiver-aware regularization to suppress residual receiver information in transmitter features while enforcing intra-receiver consistency in receiver-specific representations. A feature separation constraint is further introduced to decouple the two components in the latent space. Extensive experiments on multi-receiver WiFi datasets demonstrate that the proposed method consistently outperforms state-of-the-art baselines under cross-receiver evaluation and significantly improves robustness to receiver replacement.

تم اقتراح إطار عمل جديد لتحديد بصمة الترددات الراديوية (RFFI)، حيث يتناول التحديات التي تطرحها التغيرات الناتجة عن المستقبل في الشبكات العصبية العميقة. تركز هذه الطريقة على فصل التمثيلات الخاصة بالمرسل والمستقبل لتعزيز قوة تحديد الهوية RF عبر أجهزة مختلفة.

Se ha propuesto un nuevo marco para la identificación por huella de radiofrecuencia (RFFI), abordando los desafíos que plantea la variabilidad inducida por el receptor en las redes neuronales profundas. Este método se centra en desentrelazar las representaciones específicas del transmisor y del receptor para mejorar la robustez de la identificación RF a través de diferentes dispositivos.

Un nouveau cadre pour l'identification par empreinte radiofréquence (RFFI) a été proposé, abordant les défis posés par la variabilité induite par le récepteur dans les réseaux de neurones profonds. Cette méthode se concentre sur le désentrelacement des représentations spécifiques au transmetteur et au récepteur pour améliorer la robustesse de l'identification RF sur différents appareils.

A new framework for Radio Frequency Fingerprint Identification (RFFI) has been proposed, addressing the challenges posed by receiver-induced variability in deep neural networks. This method focuses on disentangling transmitter-specific and receiver-specific representations to enhance the robustness of RF identification across different devices.