信号处理2026，Vol.42Issue(3)：296-309,14.DOI:10.12466/xhcl.2026.03.002
基于Mamba的多域特征融合无人机射频指纹识别方法
A Mamba-Based Multi-Domain Feature Fusion Method for Radio Frequency Fingerprint Recognition of UAVs
摘要
Abstract
Radio frequency fingerprint(RFF)recognition is a key technology for target identification,enabling precise recognition of individual unmanned aerial vehicles(UAV)based solely on physical-layer signal characteristics without the need for decoding or decryption.Subtle variations in the manufacturing process of UAV radio frequency front ends lead to different devices exhibiting unique hardware nonlinearities,frequency responses,and phase noise characteris-tics,thereby forming intrinsic RFF signatures that can be used for individual differentiation.However,conventional RFF recognition methods typically rely on single-domain feature representations,leading to limited anti-interference ca-pability and inadequate modeling of dynamic signal characteristics.To address these challenges,this paper proposes an efficient multi-domain feature fusion method that deeply integrates in-phase/quadrature,bispectral,and short-time Fou-rier transform spectrogram features to enhance RFF representation.The proposed fusion architecture effectively im-proves recognition accuracy while enhancing the model's generalization capability.To overcome the computational com-plexity and real-time bottlenecks introduced by multi-domain fusion,an efficient fusion framework based on Mamba and Vision-Mamba architectures is further developed.This framework leverages the linear-time computational complex-ity of Mamba for long-sequence modeling and incorporates hardware-aware optimization strategies,thereby signifi-cantly reducing computational overhead while maintaining high recognition accuracy.Furthermore,to balance feature re-dundancy and complementarity during fusion,an adaptive cross-attention mechanism is introduced to dynamically model the interdependencies among multi-source features.This mechanism enables adaptive weighting of feature contri-butions,effectively mitigating the feature degradation caused by environmental interference.Experimental results dem-onstrate that the proposed method achieves a recognition accuracy of 97.76%while maintaining low computational cost and fast inference speed,confirming its effectiveness and superiority in UAV RFF identification.关键词
无人机/Mamba/特征融合/射频指纹/交叉注意力Key words
unmanned aerial vehicle/Mamba/feature fusion/radio frequency fingerprint/cross-attention分类
信息技术与安全科学引用本文复制引用
高大伟,聂广源,悦亚星,陈毓锋,王尹圣,郭庆华,廖桂生..基于Mamba的多域特征融合无人机射频指纹识别方法[J].信号处理,2026,42(3):296-309,14.基金项目
国家自然科学基金(62301394,62431021) （62301394,62431021）
中央高校基本科研业务费(ZYTS25035) （ZYTS25035）
西安电子科技大学创新基金(YJSJ25006) The National Natural Science Foundation of China(62301394,62431021) （YJSJ25006）
Fundamental Research Funds for the Central Universities(ZYTS25035) （ZYTS25035）
The Innovation Fund of Xidian University(YJSJ25006) （YJSJ25006）
