变调制场景下调制信息引导的双分支通信辐射源个体识别方法

王邓曦; 孙佳星; 刘辉; 黄科举; 王万泽; 杨俊安

doi:10.11999/JEIT260349

变调制场景下调制信息引导的双分支通信辐射源个体识别方法

doi: 10.11999/JEIT260349 cstr: 32379.14.JEIT260349

王邓曦¹,
孙佳星¹,
刘辉¹,
黄科举^{1, 2, ,},
王万泽¹,
杨俊安¹

1.
国防科技大学电子对抗学院合肥 230000
2.
安徽省电子制约技术重点实验室合肥 230000

基金项目: 国防科技大学自主科研基金项目

详细信息

作者简介:
王邓曦：男，博士生，研究方向为辐射源个体识别

孙佳星：男，博士，研究方向为小样本学习

刘辉：男，副教授，研究方向为通信对抗、智能信息处理

黄科举：男，讲师，研究方向为智能信号处理

王万泽：男，硕士生，研究方向为辐射源个体识别

杨俊安：男，教授，研究方向为通信对抗、智能信息处理

通讯作者:
黄科举　huangkeju@nudt.edu.cn

中图分类号: TN911.7
计量
- 文章访问数: 19
- HTML全文浏览量: 4
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2026-03-26
- 修回日期: 2026-09-09
- 录用日期: 2026-09-15
- 网络出版日期: 2026-10-10

A Modulation-Information-guided Dual-Branch Specific Emitter Identification Method Under Variable Modulation Scenarios

1.
College of Electronic Engineering, National University of Defense Technology, Hefei 230000, China
2.
Anhui province key laboratory of electronic restriction, Hefei 230000, China

Funds: Innovation Research Foundation of National University of Defense Technology

摘要

摘要: 通信辐射源调制参数的动态变化，给辐射源个体识别(SEI)性能带来严峻挑战。针对现有基于域适应的变调制SEI方法存在特征鲁棒性不足、过度依赖目标域数据重训练的问题，本文首次将域泛化方法引入该任务，提出一种调制信息引导的双分支训练框架(MIG-DTF)及测试阶段模型适应策略(TMA)。MIG-DTF采用个体识别主分支与调制分类辅助分支协同训练模式。主分支引入余弦聚合损失以强化指纹特征的区分度，辅助分支通过最大化交叉预测熵损失，引导主分支抑制指纹特征中的调制相关信息，从而实现对调制变化鲁棒的指纹特征提取。测试时采用TMA自适应策略单步微调批归一化层参数，以改善失配参数对特征造成的分布偏移，进一步提升识别准确率。基于真实数据集，在变调制样式、变载频、变符号速率三种典型场景下开展对比实验，结果表明，所提方法的识别率显著优于主流域泛化方法，较基线方法在三个场景中分别提升20.39%、12.43%和14.51%。特征可视化分析与抗噪声实验进一步验证了该方法能够有效提取对调制变化鲁棒的指纹特征，以及良好的抗噪声鲁棒性。此外，得益于TMA单步微调的极低训练开销，及无需目标域训练样本特性，本方法更具实际部署前景。
- 通信辐射源个体识别 /
- 深度学习 /
- 领域泛化 /
- 变调制参数
Abstract: Objective Specific Emitter Identification (SEI) relies on Radio Frequency Fingerprints (RFFs) for emitter discrimination, widely used in military reconnaissance and IoT authentication. Traditional SEI only works under fixed modulation parameters, and existing Domain Adaptation (DA) methods lack robust features and rely heavily on target-domain retraining for variable-modulation SEI. To address these limitations, this paper pioneers the application of Domain Generalization (DG) to variable-modulation SEI, proposing a Modulation-Information-guided Dual-branch Training Framework (MIG-DTF) with a Test-Time Adaptation strategy (TMA). This method extracts modulation-invariant RFFs without large-scale target domain retraining, improves SEI accuracy under variations in multiple common modulation parameters. Methods The proposed method consists of training and testing stages. MIG-DTF serves as the core of the training stage, composed of an emitter identification main branch and a modulation classification auxiliary branch for collaborative training. The main branch innovatively adopts cosine aggregation loss to enhance the discriminability of RFFs, while the auxiliary branch maximizes the cross-prediction entropy to guide the main branch to filter out modulation-related information and extract modulation-invariant robust RFFs. At test time, TMA performs one-step fine-tuning on the BN layer parameters under the entropy minimization objective based on the test samples. This corrects the parameter mismatch of BN layers between training and test domains, alleviates the drift of feature distribution, and improves the identification accuracy. Results and Discussions Experiments on a real-world variable-modulation dataset validate the proposed method’s effectiveness. Comparisons against mainstream DG methods yield identification accuracies of 79.31% (Table 1), 87.39% (Table 2) and 88.33% (Table 3) under variable modulation type, carrier frequency and symbol rate, respectively. Ablation studies validate the individual and combined performance gains of MIG-DTF and TMA (Fig. 4). Feature visualization verifies that the extracted modulation-invariant RFFs exhibit intra-class compactness and inter-class separability (Fig. 5), and quantitative correlation analysis with modulation labels demonstrates their superior modulation invariance over baseline (Table 5). Across 10–30 dB SNR anti-noise tests, the proposed method surpasses the baseline with a minimum 10% accuracy gain at 10 dB (Fig. 7), showing remarkable noise robustness. Overhead analysis indicates TMA reduces training costs and eliminates target-domain training data requirements, facilitating practical deployment. Conclusions This paper tackles robust SEI under variable modulation scenarios via the training-stage MIG-DTF and testing-stage TMA strategy. The proposed method improves SEI performance by extracting modulation-invariant RFFs with MIG-DTF and enabling fast model fine-tuning via TMA without extra target domain retraining. Comprehensive experiments on a real-world dataset validate the method: (1) The proposed method exhibits superior identification accuracy against mainstream DG methods; (2) Feature visualization verifies its effective extraction of discriminative modulation-invariant RFFs; (3) The method exhibits satisfactory anti-noise robustness in noise-added experiments; (4) TMA boasts minimal computational overhead and requires no target-domain training data, facilitating practical deployment. However, this study only considers modulation variations, and more complex practical scenarios, such as time-varying channel conditions, should be involved in future work.
- Specific Emitter Identification /
- Deep Learning /
- Domain Generalization /
- Variable Modulation

HTML全文

图 1 本文方法的总体框架图

下载: 全尺寸图片幻灯片

图 2 测试阶段TMA方法示意图

下载: 全尺寸图片幻灯片

图 3 Net_F与Net_M网络结构图

下载: 全尺寸图片幻灯片

图 4 三种变参数场景下的消融实验

下载: 全尺寸图片幻灯片

图 5 Baseline与本文方法的特征可视化对比

下载: 全尺寸图片幻灯片

图 6 指纹特征与调制特征进行调制分类的训练准确率曲线

下载: 全尺寸图片幻灯片

图 7 识别准确率随信噪比变化曲线

下载: 全尺寸图片幻灯片

表 1 变调制样式场景下不同方法的识别准确率对比(%)

算法	BP, QP→8P	BP, 8P→QP	QP, 8P→BP	QP, 8P→QAM	BP, QP→QAM	均值
Baseline	70.65±4.83	85.04±4.15	62.76±4.85	34.66±0.45	41.49±7.36	58.92
CORAL	91.00±0.24	86.53±3.10	65.56±2.57	33.57±3.84	48.27±6.20	64.99
V-REx	80.29±1.77	86.56±1.86	66.00±1.36	38.13±0.27	48.33±2.00	63.86
RIEI	89.62±3.64	87.31±2.65	65.31±0.98	37.38±0.36	39.84±0.31	63.89
CDDG	90.45±4.44	89.31±0.16	66.62±0.80	32.66±2.89	49.27±8.23	65.66
本文方法	84.89±2.72	89.11±0.44	81.74±2.67	66.34±0.31	74.49±2.67	79.31

下载: 导出CSV

表 2 变载频场景下不同方法的识别准确率对比(%)

算法	F1, F2→F3	F1, F3→F2	F2, F3→F1	均值
Baseline	80.45±3.03	66.93±2.98	77.49±2.37	74.96
CORAL	86.87±2.89	63.56±2.73	75.69±2.18	75.37
V-REx	88.69±1.52	73.51±2.33	80.38±1.08	80.86
RIEI	82.64±0.93	68.98±2.04	77.73±1.46	76.45
CDDG	86.40±1.42	66.24±1.51	76.45±1.30	76.36
本文方法	89.26±0.13	88.49±0.14	84.43±0.27	87.39

下载: 导出CSV

表 3 变符号速率场景下不同方法的识别准确率对比(%)

算法	R1, R2→R3	R1, R3→R2	R2, R3→R1	均值
Baseline	55.33±0.99	94.51±4.11	71.62±4.67	73.82
CORAL	56.33±1.87	98.98±0.38	69.07±1.20	74.79
V-REx	61.29±2.76	95.53±2.08	69.82±4.42	75.55
RIEI	56.50±1.06	98.53±1.16	82.60±3.91	79.21
CDDG	57.78±0.22	99.13±0.11	79.86±6.71	78.92
本文方法	66.58±0.71	99.80±0.04	98.62±0.53	88.33

下载: 导出CSV

表 4 TMA与DA的开销对比

阶段	更新参数量	单轮耗时
MIG-DTF训练	1.12 M	5.36 s
测试	0	0.75 s
TMA模型微调	1.60 K	0.79 s
DA模型重训练	561.27 K	2.15 s

下载: 导出CSV

表 5 特征与调制标签、个体标签的第一典型相关系数$ \rho $值

方法	实验组	特征与调制标签	特征与个体标签
Baseline	BP, 8P→QP	0.9636	0.9975
Baseline	R1, R3→R2	0.9823	0.9905
本文方法	BP, 8P→QP	0.3833	0.9926
本文方法	R1, R3→R2	0.4185	0.9870

下载: 导出CSV

参考文献(26)

[1]	刘高辉, 席宏恩. 改进变分模态分解与多特征的通信辐射源个体识别方法[J]. 电子与信息学报, 2024, 46(10): 4044–4052. doi: 10.11999/JEIT231348. LIU Gaohui and XI Hongen. Individual identification method for communication emitters based on improved variational modal decomposition and multiple features[J]. Journal of Electronics & Information Technology, 2024, 46(10): 4044–4052. doi: 10.11999/JEIT231348.
[2]	DANEV B, HEYDT-BENJAMIN T S, and ČAPKUN S. Physical-layer identification of RFID devices[C]. Proceedings of the 18th Conference on USENIX Security Symposium, Montreal, Canada, 2009: 199–214.
[3]	ZHANG Jingwen, WANG Fanggang, DOBRE O A, et al. Specific emitter identification via Hilbert-Huang transform in single-hop and relaying scenarios[J]. IEEE Transactions on Information Forensics and Security, 2016, 11(6): 1192–1205. doi: 10.1109/TIFS.2016.2520908.
[4]	SATIJA U, TRIVEDI N, BISWAL G, et al. Specific emitter identification based on variational mode decomposition and spectral features in single hop and relaying scenarios[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(3): 581–591. doi: 10.1109/TIFS.2018.2855665.
[5]	FU Hua, SUN Yanfeng, PENG Linning, et al. Channel-resilient RF fingerprint identification based on nonlinear features with memory effect[J]. IEEE Communications Letters, 2024, 28(4): 798–802. doi: 10.1109/LCOMM.2024.3364494.
[6]	肖易寒, 王博煜, 于祥祯, 等. 基于双路射频指纹卷积神经网络与特征融合的雷达辐射源个体识别[J]. 电子与信息学报, 2024, 46(8): 3238–3245. doi: 10.11999/JEIT231236. XIAO Yihan, WANG Boyu, YU Xiangzhen, et al. Radar emitter identification based on dual radio frequency fingerprint convolutional neural network and feature fusion[J]. Journal of Electronics & Information Technology, 2024, 46(8): 3238–3245. doi: 10.11999/JEIT231236.
[7]	GIUSTINIANO D, SCHALCH M, LIECHTI M, et al. Interference suppression in bandwidth hopping spread spectrum communications[C]. Proceedings of the 11th ACM Conference on Security & Privacy in Wireless and Mobile Networks, Stockholm, Sweden, 2018: 134–143. doi: 10.1145/3212480.3212484.
[8]	HUANG Keju, YANG Junan, LIU Hui, et al. Deep adversarial neural network for specific emitter identification under varying frequency[J]. Bulletin of the Polish Academy of Sciences-Technical Sciences, 2021, 69(2): e136737. doi: 10.24425/bpasts.2021.136737.
[9]	ZHANG Xinliang, LI Tianyun, GONG Pei, et al. Variable-modulation specific emitter identification with domain adaptation[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 380–395. doi: 10.1109/TIFS.2022.3223794.
[10]	YIN Lijun, FU Xue, SHI Shengnan, et al. Few-shot domain adaption-based specific emitter identification under varying modulation[C]. 2023 IEEE 23rd International Conference on Communication Technology (ICCT), Wuxi, China, 2023: 1439–1443. doi: 10.1109/ICCT59356.2023.10419733.
[11]	HE Yazhe and ZHANG Qin. Cross-modulation specific emitter identification based on source-free domain adaptation[C]. 2025 10th International Conference on Computer and Communication System (ICCCS), Chengdu, China, 2025: 458–463. doi: 10.1109/ICCCS65393.2025.11069648.
[12]	LI Ying, WANG Xingwei, ZENG Rongfei, et al. Federated domain generalization: A survey[J]. Proceedings of the IEEE, 2025, 113(4): 370–410. doi: 10.1109/JPROC.2025.3596173.
[13]	王雪安. 基于循环谱的调制方式盲识别与频偏估计[D]. [硕士论文], 北京邮电大学, 2017. WANG Xuean. Modulation blind recognition and frequency offset estimation based on cyclic spectrum[D]. [Master dissertation], Beijing University of Posts and Telecommunications, 2017.
[14]	DI ROSA G and RICHTER A. Low complexity blind carrier phase recovery for probabilistically shaped QAM[J]. IEEE Photonics Technology Letters, 2020, 32(17): 1109–1112. doi: 10.1109/LPT.2020.3012970.
[15]	LIM D. A modified Gardner detector for symbol timing recovery of M-PSK signals[J]. IEEE Transactions on Communications, 2004, 52(10): 1643–1647. doi: 10.1109/TCOMM.2004.836450.
[16]	MAO Anqi, MOHRI M, and ZHONG Yutao. Cross-entropy loss functions: Theoretical analysis and applications[C]. 40th International Conference on Machine Learning, Honolulu, USA, 2023: 23803–23828.
[17]	MAHAJAN D, TOPLE S, and SHARMA A. Domain generalization using causal matching[C]. Proceedings of the 38th International Conference on Machine Learning, 2021: 7313–7324. (查阅网上资料, 未找到本条文献出版地信息, 请确认).
[18]	WU Zhize, DU Changjiang, WANG Xinqi, et al. Domain Adaptation via Feature Disentanglement for cross-domain image classification[J]. Applied Soft Computing, 2025, 172: 112868. doi: 10.1016/j.asoc.2025.112868.
[19]	SU Kejia, LIU Kai, WAN Bo, et al. Multisource adversarial feature disentanglement method for cross-subject gesture recognition using sEMG signals[J]. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 4508912. doi: 10.1109/TIM.2025.3557823.
[20]	WANG Dequan, SHELHAMER E, LIU Shaoteng, et al. Tent: Fully test-time adaptation by entropy minimization[C]. 9th International Conference on Learning Representations, 2021. (查阅网上资料, 未找到本条文献出版地信息, 请确认).
[21]	SUN Baochen and SAENKO K. Deep CORAL: Correlation alignment for deep domain adaptation[C]. Computer Vision – ECCV 2016 Workshops, Amsterdam, The Netherlands, 2016: 443–450.
[22]	KRUEGER D, CABALLERO E, JACOBSEN J H, et al. Out-of-distribution generalization via risk extrapolation[C]. Proceedings of the 38th International Conference on Machine Learning, 2021: 5815–5826. (查阅网上资料, 未找到本条文献出版地信息, 请确认).
[23]	ZHANG Ying, LI Qiang, LIU Hongli, et al. Domain generalization for cross-receiver radio frequency fingerprint identification[J]. IEEE Internet of Things Journal, 2025, 12(5): 5207–5218. doi: 10.1109/JIOT.2024.3486068.
[24]	JIA Linshan, CHOW T W C, and YUAN Yixuan. Causal Disentanglement Domain Generalization for time-series signal fault diagnosis[J]. Neural Networks, 2024, 172: 106099. doi: 10.1016/j.neunet.2024.106099.
[25]	LU Weipeng and YAN Xuefeng. Visual high dimensional industrial process monitoring based on deep discriminant features and t-SNE[J]. Multidimensional Systems and Signal Processing, 2021, 32(2): 767–789. doi: 10.1007/s11045-020-00758-5.
[26]	HARDOON D R, SZEDMAK S, and SHAWE-TAYLOR J. Canonical correlation analysis: An overview with application to learning methods[J]. Neural Computation, 2004, 16(12): 2639–2664. doi: 10.1162/0899766042321814.