基于Transformer多参数加权融合的GNSS欺骗干扰检测

doi:10.12305/j.issn.1001-506X.2026.07.27

摘要/Abstract

摘要：

针对传统全球卫星导航系统（global navigation satellite system，GNSS）欺骗干扰检测方法场景适应性不足，以及现有机器学习模型虚警率高、泛化性能差等问题，提出一种基于Transformer多参数加权融合的GNSS欺骗干扰检测方法。该方法考虑了欺骗干扰在跟踪阶段产生的异常参数变化，采用相关器输出指标、载噪比等多参数加权融合的方式将多个特征进行融合，提升模型对特征扰动的灵敏度，同时通过特征维度压缩有效提高了模型训练效率。实验结果表明，所提方法在TEXBAT、OAKBAT、FGI-SpoofRepo 3种不同的数据集上均可以达到100%的检测准确率和F1-Score。本文所提方法与传统的假设检验方法和支持向量机模型相比，显著提升了欺骗干扰检测的准确率与鲁棒性，其多参数加权融合机制为后续抗干扰接收机设计提供了新的理论支撑。

关键词: 卫星导航, 欺骗检测, 多参数加权融合, Transformer

Abstract:

To address the insufficient scenario adaptability of conventional global navigation satellite system （GNSS） spoofing detection methods and the challenges of high false alarm rates and poor generalization in existing machine learning models, a GNSS spoofing interference detection method based on Transformer multi-parameter weighted fusion is proposed. The method considers abnormal parameter variations induced by spoofing interference during the tracking phase, and employs multi-parameter weighted fusion of correlator output metrics, carrier-to-noise ratio and other multidimensional features to enhance the model’s sensitivity to characteristic perturbations. Furthermore, feature dimension compression effectively improves model training efficiency. Experimental results demonstrate that the proposed method achieves 100% detection accuracy and F1-Score across three distinct datasets: TEXBAT, OAKBAT, and FGI-SpoofRepo. Compared with conventional hypothesis testing methods and support vector machine models, the proposed method significantly enhances both detection accuracy and robustness against spoofing interference. The developed multi-parameter weighted fusion mechanism establishes novel theoretical foundations for subsequent anti-jamming receiver design.

Key words: satellite navigation, spoofing detection, multi-parameter weighted fusion, Transformer

中图分类号:

TN 97

郝志雨, 刘小汇, 赵小宇, 李宗楠, 鲁祖坤. 基于Transformer多参数加权融合的GNSS欺骗干扰检测[J]. 系统工程与电子技术, 2026, 48(7): 2434-2447.

Zhiyu HAO, Xiaohui LIU, Xiaoyu ZHAO, Zongnan LI, Zukun LU. GNSS spoofing interference detection based on Transformer multi-parameter weighted fusion[J]. Systems Engineering and Electronics, 2026, 48(7): 2434-2447.

图/表 19

图1

图2

图3

图4

表1

表2

图5

表3

图6

表4

图7

表5

图8

图9

表6

表7

表8

表9

图10

参考文献 31

1	HEGARTY C J, CHATRE E. Evolution of the global navigation satellite system （GNSS）[J]. Proceedings of the IEEE, 2008, 96 (12): 1902- 1917. doi: 10.1109/JPROC.2008.2006090
2	YAN P H, JIANG J G, TAN H B, et al. High precision time synchronization strategy for low-cost embedded GNSS/MEMS-IMU integrated navigation module[J]. IEEE Trans. on Intelligent Transportation Systems, 2024, 25 (10): 14087- 14099. doi: 10.1109/TITS.2024.3386970
3	CHEN L, ZHENG F, GONG X P, et al. GNSS high-precision augmentation for autonomous vehicles: requirements, solution, and technical challenges[J]. Remote Sensing, 2023, 15 (6): 1623. doi: 10.3390/rs15061623
4	WU Y, MENG H, YAN H W. Adaptive positioning and tracking system for military equipment based on Beidou satellites[C]//Proc. of the IEEE International Conference on Sustainable Computing and Data Communication Systems, 2022: 724−727.
5	LI X J, LU Z K, YUAN M Z, et al. Tradeoff of code estimation error rate and terminal gain in SCER attack[J]. IEEE Trans. on Instrumentation and Measurement, 2024, 73, 8504512.
6	刘小汇, 王怡晨, 文超, 等. 复杂城市环境下的全球导航卫星系统/捷联惯性导航系统组合导航算法[J]. 电子与信息学报, 2023, 45 (11): 4150- 4160. doi: 10.11999/JEIT230834
	LIU X H, WANG Y C, WEN C, et al. Global navigation satellite system/strapdown inertial navigation system integrated navigation algorithm in complex urban environment[J]. Journal of Electronics and Information Technology, 2023, 45 (11): 4150- 4160. doi: 10.11999/JEIT230834
7	HUMPHREYS T E, LEDVINA B M, PSIAKI M L, et al. Assessing the spoofing threat: development of a portable GPS civilian spoofer [C]//Proc. of the International Technical Meeting of the Satellite Division of the Institute of Navigation, 2008.
8	MAHROOF A, NABI I, FAROOQ S Z, et al. Machine learning-based detection of spoofing attacks in GNSS: a study using TEXBAT dataset[C]//Proc. of the 14th International Conference on Electrical Engineering, 2024: 90−95.
9	LI J, CHEN Z K, RAN Z X, et al. The GNSS spoofing detection method based on AdaBoost[C]//Proc. of the 6th International Symposium on Autonomous Systems, 2023.
10	CHEN Z K, LI J Z, LI J, et al. GNSS multiparameter spoofing detection method based on support vector machine[J]. IEEE Sensors Journal, 2022, 22 (18): 17864- 17874. doi: 10.1109/JSEN.2022.3193388
11	ALHORAIBI L, ALGHAZZAWI D, ALHEBSHI R. Detection of GPS spoofing attacks in UAVs based on adversarial machine learning model[J]. Sensors, 2024, 24 (18): 6156. doi: 10.3390/s24186156
12	GUIZZARO C, FORMAGGIO F, TOMASIN S. GNSS spoofing attack detection by IMU measurements through a neural network[C]//Proc. of the 10th Workshop on Satellite Navigation Technology, 2022.
13	AISSOU G, BENOUADAH S, EL ALAMI H, et al. Instance-based supervised machine learning models for detecting GPS spoofing attacks on UAS[C]//Proc. of the IEEE 12th Annual Computing and Communication Workshop and Conference, 2022: 208−214.
14	AISSOU G, SLIMANE H O, BENOUADAH S, et al. Tree-based supervised machine learning models for detecting GPS spoofing attacks on UAS[C]//Proc. of the IEEE 12th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference, 2021: 649−653.
15	FENG Z, SEOW C K, CAO Q. GNSS anti-spoofing detection based on Gaussian mixture model machine learning[C]//Proc. of the IEEE 25th International Conference on Intelligent Transportation Systems, 2022: 3334−3339.
16	SHAFIQUE A, MEHMOOD A, ELHADEF M. Detecting signal spoofing attack in UAVs using machine learning models[J]. IEEE Access, 2021, 9, 93803- 93815. doi: 10.1109/ACCESS.2021.3089847
17	FANG J X T, YUE J, XU B, et al. A post-correlation graphical way for continuous GNSS spoofing detection[J]. Measurement, 2023, 216, 112974. doi: 10.1016/j.measurement.2023.112974
18	LI J Z, ZHU X W, OUYANG M J, et al. GNSS spoofing jamming detection based on generative adversarial network[J]. IEEE Sensors Journal, 2021, 21 (20): 22823- 22832. doi: 10.1109/JSEN.2021.3105404
19	LIU Y, XU B, CHEN Z K, et al. Detection and mitigation of time synchronization attacks based on long short-term memory neural network[J]. GPS Solutions, 2024, 28 (1): 46. doi: 10.1007/s10291-023-01587-2
20	REN Y Y, RESTIVO R D, TAN W K, et al. Knowledge distillation-based GPS spoofing detection for small UAV[J]. Future Internet, 2023, 15 (12): 389. doi: 10.3390/fi15120389
21	NIU B, ZHUANG X B, HE Y Z, et al. Navigation deception signal detection based on ensemble learning[C]//Proc. of the IEEE International Conference on Unmanned Systems, 2023: 859−864.
22	谢钢. GPS 原理与接收机设计[M]. 北京: 电子工业出版社, 2009: 303−325.
	XIE G. GPS principles and receiver design [M]. Beijing: Publishing House of Electronics Industry, 2009: 303−325.
23	梁高波, 高义, 陈杨. 欺骗式干扰信号对GPS民用接收机的影响分析[C]//第四届中国卫星导航学术年会, 2013.
	LIANG G B, GAO Y, CHEN Y. The effect of spoof-jamming signals on GPS civil receiver[C]//Proc. of the 4th China Satellite Navigation Academic Conference, 2013.
24	陈静, 陈思源, 刘鹏. GNSS转发式欺骗干扰对接收机的影响分析[C]//第九届中国卫星导航学术年会, 2018.
	CHEN J, CHEN S Y, LIU P. Analysis of GNSS repeater deception jamming signal effect on the receiver[C]//Proc. of the 9th China Satellite Navigation Academic Conference, 2018.
25	LIN T Y, WANG Y X, LIU X Y, et al. A survey of transformers[J]. AI Open, 2022, 3, 111- 132. doi: 10.1016/j.aiopen.2022.10.001
26	HAN K, WANG Y H, CHEN H T, et al. A survey on vision transformer[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2023, 45 (1): 87- 110. doi: 10.1109/TPAMI.2022.3152247
27	YI T, DEHGHANI M, BAHRI D, et al. Efficient transformers: a survey[J]. Association for Computing Machinery, 2022, 55 (6): 28.
28	HUMPHREYS T E, BHATTI J A, SHEPARD D P, et al. The texas spoofing test battery: toward a standard for evaluating GPS signal authentication techniques[C]//Proc. of the 25th International Technical Meeting of the Satellite Division of the institute of Navigation, 2012.
29	LEMMENES C A, GUNAWARDENA D S. Detailed analysis of the TEXBAT datasets using a high fidelity software GPS receiver[C]//Proc. of the 29th International Technical Meeting of the Satellite Division of the Institute of Navigation, 2016.
30	AUSTIN A, SARAH P, JASON B, et al. A tool for furthering GNSS security research: the oak ridge spoofing and interference test battery (OAKBAT) [C]//Proc. of the 33rd International Technical Meeting of the Satellite Division of the Institute of Navigation, 2020.
31	SAIFUL I, MOHAMMAD ZAHIDUL H. B, MUWAHIDA L, et al. An open GNSS spoofing data repository: characterization and impact analysis with FGI-GSRx open-source software-defined receiver[J]. GPS Solutions, 2024, 28 (4): 176. doi: 10.1007/s10291-024-01719-2

参数名称	参数值
编码器层数	3
多头注意力机制的头数	4
模型维度（嵌入维度）	128
前馈神经网络层的隐藏维度	128
批量大小	64
全连接层前的全局Dropout率	0.3

数据集名称	${w_{11}}$	${w_{12}}$	${w_{13}}$	${w_{14}}$
Texbat-ds2	0.1095	0.5349	0.2381	0.1175
Texbat-ds5	0.1797	0.2567	0.3843	0.1793
Oakbat-os3	0.2470	0.2553	0.2507	0.2470
FGI_TGD	0.2450	0.2441	0.2600	0.2509

数据集名称	${w_{21}}$	${w_{22}}$	${w_{23}}$	${w_{24}}$
Texbat-ds2	0.3707	0.3789	0.1661	0.0844
Texbat-ds5	0.8152	0.0474	0.0869	0.0505
Oakbat-os3	0.0254	0.0798	0.7911	0.7911
FGI_TGD	0.1913	0.1649	0.3278	0.3161

参数组合	参数选择
Case 1	${h_9}(n)$
Case 2	${h_{10}}(n)$
Case 3	$ {h_1}(n) + {h_2}(n) + {h_3}(n) + {h_4}(n) $
Case 4	${h_9}(n) + {h_{10}}(n)$
Case 5	$ {h_5}(n) + {h_6}(n) + {h_7}(n) + {h_8}(n) $
Case 6	${h_{10}}(n) + {\mathrm{Doppler}} + {\mathrm{carrPhase}} $
Case 7	${h_9}(n) + {h_{10}}(n) + {\mathrm{Doppler}} $
Case 8	$ h_1(n) \sim h_{10}(n)+ { {\mathrm{Doppler}} }+C / N_0+ { {\mathrm{carrPhase}} }$

卫星PRN	假设检验	Transformer	卫星PRN	假设检验	Transformer
GPS-03	0.92	0.97	GPS-16	0.81	0.97
GPS-06	0.76	0.97	GPS-19	0.72	0.93
GPS-13	0.93	0.98	GPS-23	0.96	0.99

真实标签	预测标签
真实标签	欺骗信号	真实信号
欺骗信号	TP	FN
真实信号	FP	TN