非合作对抗场景下的隐真示假调制识别方法

尹志胜; 张智杰; 承楠; 刘怡良; 王威

doi:10.12263/DZXB.20251167

您当前的位置：

首页 >

文章列表页 >

非合作对抗场景下的隐真示假调制识别方法

学术论文 | 更新时间：2026-05-28

- 非合作对抗场景下的隐真示假调制识别方法
- Automatic Modulation Recognition Method via Conceal-Truth-While-Showing-Fake Strategy in Non-Cooperative Adversarial Scenarios
- 电子学报 2026年54卷第2期页码：507-516
- 作者机构：
  
  1.西安电子科技大学通信工程学院，陕西西安 710071
  2.空天地一体化综合业务网全国重点实验室，陕西西安 710071
  3.西安交通大学网络空间安全学院，陕西西安 710049
  4.西安交通大学信息与通信工程学院，陕西西安 710049
- 作者简介：
  
  [ "尹志胜男，西安电子科技大学通信工程学院副教授、硕士生导师。主要研究方向为空天地一体化网络、无线通信系统、面向6G的星地一体高效接入与传输技术、星地物理层安全通信方法、智能传输技术等。 E-mail: zsyin@xidian.edu.cn" ]
  [ "张智杰男，西安电子科技大学通信工程学院硕士研究生。主要研究方向为通信对抗技术、人工智能算法等。 E-mail: zhangzhijie@stu.xidian.edu.cn" ]
  [ "承楠男，西安电子科技大学通信工程学院教授、博士生导师。主要研究方向为智能车联网及先进交通系统、空天地一体化网络、人工智能与大数据技术在网络中的应用。中国电子学会会员编号：E190130905M。 E-mail: nancheng@xidian.edu.cn" ]
  [ "刘怡良男，西安交通大学网络空间安全学院副教授、博士生导师。主要研究方向为下一代无线通信、信息安全、物理层安全。E-mail: liuyiliang@xjtu.edu.cn" ]
  [ "王威男，西安交通大学信息与通信工程学院教授、博士生导师。主要研究方向为下一代无线通信技术、网络与电磁安全。中国电子学会会员编号：E190026972S。 E-mail: w25wang@xjtu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62201432)
- DOI：10.12263/DZXB.20251167
  中图分类号： TN975;TP309
- 收稿：2026-01-06，
  
  录用：2026-01-26，
  
  纸质出版：2026-02-25
- 稿件说明：
移动端阅览
尹志胜, 张智杰, 承楠, 等. 非合作对抗场景下的隐真示假调制识别方法[J]. 电子学报, 2026, 54(02): 507-516.

YIN Zhisheng, ZHANG Zhijie, CHENG Nan, et al. Automatic Modulation Recognition Method via Conceal-Truth-While-Showing-Fake Strategy in Non-Cooperative Adversarial Scenarios[J]. Acta Electronica Sinica, 2026, 54(02): 507-516.
尹志胜, 张智杰, 承楠, 等. 非合作对抗场景下的隐真示假调制识别方法[J]. 电子学报, 2026, 54(02): 507-516. DOI：10.12263/DZXB.20251167

YIN Zhisheng, ZHANG Zhijie, CHENG Nan, et al. Automatic Modulation Recognition Method via Conceal-Truth-While-Showing-Fake Strategy in Non-Cooperative Adversarial Scenarios[J]. Acta Electronica Sinica, 2026, 54(02): 507-516. DOI：10.12263/DZXB.20251167

摘要

针对非合作对抗通信场景中信号易被截获和通信意图易暴露的安全威胁，本文突破传统被动防御范式，提出面向智能电子设备中自动调制识别（Automatic Modulation Recognition， AMR）的隐真示假调制识别方法，实现对抗场景下合作链路的可靠传输与非合作链路的精准诱骗。考虑多输入多输出信道在时-频-空域呈现的多维差异性特征，本文设计了基于主-窃信道特征提取的数据标签投毒方法，实现了诱骗非合作方AMR模型的隐蔽后门触发机制，同时保证合作方准确可靠的识别率。此方法赋予通信设备主动防御能力，从物理层阻断了非合作方利用同源技术设备实施信号窃取的路径。本文在对多种AMR模型进行基线性能比较的基础上，进一步评估了所提方法在不同天线配置、投毒率、误导策略及信道估计相位误差下的性能表现。基于典型AMR模型的实验结果表明，在投毒率

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262372&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262348&type=

8.72066593

2.87866688

时，多输入多输出（Multiple-Input Multiple-Output，MIMO）

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262384&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262364&type=

6.01133299

2.28600001

场景下的攻击成功率（Attack Success Rate， ASR）达到89.94%，相较于单输入单输出（Single-Input Single-Output，SISO）场景下的76.28%显著提升了13.66%，且合作用户的良性准确率（Benign Accuracy，BA）维持在89.65%。此外，在投毒率

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262365&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262350&type=

8.72066593

2.87866688

且存在上限为

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262352&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262374&type=

3.21733332

2.28600001

°的信道估计相位偏差下，本方法的ASR仍能保持在89.21%，同时保证合作用户的BA为87.79%，表明本方法在保障合作用户通信可靠性的同时，具备针对非合作用户的高效且鲁棒的误导能力，为复杂通信环境下的物理层安全通信提供了新的技术范式。

Abstract

Against the security threats of signal interception and communication intent exposure in non-cooperative adversarial communication scenarios

this paper proposes the conceal-truth-while-showing-fake modulation recognition method

breaking the traditional passive defense paradigm

for automatic modulation recognition (AMR) in intelligent electronic de

vices. This approach achieves reliable transmission for cooperative links and precise deception for non-cooperative links in adversarial environments. Leveraging the multi-dimensional characteristics of multiple-input multiple-output (MIMO) channels in the time-frequency-spatial domains

this paper designs a data label poisoning method based on feature extraction of the legitimate-eavesdropper channels

which realizes a covert backdoor trigger mechanism to mislead non-cooperative AMR models while ensuring the accurate and reliable recognition rate of the cooperative party. This method endows communication devices with active defense capabilities and blocks the path for non-cooperative parties to conduct signal theft by utilizing homologous technical equipment from the physical layer. Based on the baseline performance comparison of various AMR models

this paper further evaluates the performance of the proposed method under different antenna configurations

poisoning rates

deception strategies

and channel estimation phase errors. The experimental results based on typical AMR models show that at a poisoning rate of

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262386&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262398&type=

8.72066593

2.87866688

the attack success rate (ASR) of the method reaches 89.94% in the 4×4 MIMO scenario

a significant increase of 13.66% compared with 76.28% in the single-input single-output (SISO) scenario

while the benign accuracy (BA) of cooperative users is maintained at 89.65%. In addition

at a poisoning rate of

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262399&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262387&type=

8.72066593

2.87866688

and with a maximum channel estimation phase deviation of

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262400&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=109262376&type=

3.21733332

2.28600001

the ASR of the proposed method can still be maintained at 89.21%

and the BA of cooperative users is guaranteed to be 87.79%. This demonstrates that the proposed method not only ensures the communication reliability of cooperative users but also possesses efficient and robust misleading capabilities against non-cooperative users

providing a new technical paradigm for physical layer security in complex communication environments.

关键词

Keywords

references

Zhao Junhui , Liu Congcong , Liao Jieyu , et al . Deep learning in wireless communications for physical layer [J ] . Physical Communication , 2024 , 67 : 102503 . DOI: 10.1016/j.phycom.2024.102503 http://dx.doi.org/10.1016/j.phycom.2024.102503

张正宇 , 何睿斯 , 杨汨 , 等 . 面向6G的无线信道语义特征及建模 [J ] . 电子学报 , 2025 , 53 ( 1 ): 14 - 23 . DOI: 10.23919/cje.2024.00.003 http://dx.doi.org/10.23919/cje.2024.00.003

Zhang Zhengyu , He Ruisi , Yang Mi , et al . Semantic characteristics and modeling of wireless channels for 6G [J ] . Acta Electronica Sinica , 2025 , 53 ( 1 ): 14 - 23 . (in Chinese) . DOI: 10.23919/cje.2024.00.003 http://dx.doi.org/10.23919/cje.2024.00.003

Zhang Shunliang , Zhu Dali , Liu Yinlong . Artificial intelligence empowered physical layer security for 6G: State-of-the-art, challenges, and opportunities [J ] . Computer Networks , 2024 , 242 : 110255 . DOI: 10.1016/j.comnet.2024.110255 http://dx.doi.org/10.1016/j.comnet.2024.110255

Li Mingfang , Dou Zheng . Active eavesdropping detection: A novel physical layer security in wireless IoT [J ] . EURASIP Journal on Advances in Signal Processing , 2023 , 2023 : 119 . DOI: 10.1186/s13634-023-01080-5 http://dx.doi.org/10.1186/s13634-023-01080-5

Marchioro T , Laurenti N , Gunduz D . Adversarial networks for secure wireless communications [C ] // ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2020 : 8748 - 8752 . DOI: 10.1109/icassp40776.2020.9053216 http://dx.doi.org/10.1109/icassp40776.2020.9053216

Jdid B , Hassan K , Dayoub I , et al . Machine learning based automatic modulation recognition for wireless communications: A comprehensive survey [J ] . IEEE Access , 2021 , 9 : 57851 - 57873 . DOI: 10.1109/access.2021.3071801 http://dx.doi.org/10.1109/access.2021.3071801

Peng Shengliang , Sun Shujun , Yao Yudong . A survey of modulation classification using deep learning: Signal representation and data preprocessing [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2022 , 33 ( 12 ): 7020 - 7038 . DOI: 10.1109/tnnls.2021.3085433 http://dx.doi.org/10.1109/tnnls.2021.3085433

Dobre O A , Abdi A , Bar-Ness Y , et al . Survey of automatic modulation classification techniques: Classical approaches and new trends [J ] . IET Communications , 2007 , 1 ( 2 ): 137 - 156 . DOI: 10.1049/iet-com:20050176 http://dx.doi.org/10.1049/iet-com:20050176

Swami A , Sadler B M . Hierarchical digital modulation classification using cumulants [J ] . IEEE Transactions on Communications , 2000 , 48 ( 3 ): 416 - 429 . DOI: 10.1109/26.837045 http://dx.doi.org/10.1109/26.837045

O’Shea T J , Corgan J , Clancy T C . Convolutional radio modulation recognition networks [C ] // Engineering Applications of Neural Networks . Cham : Springer , 2016 : 213 - 226 . DOI: 10.1007/978-3-319-44188-7_16 http://dx.doi.org/10.1007/978-3-319-44188-7_16

Gu Tianyu , Liu Kang , Dolan-Gavitt B , et al . BadNets: Evaluating backdooring attacks on deep neural networks [J ] . IEEE Access , 2019 , 7 : 47230 - 47244 . DOI: 10.1109/access.2019.2909068 http://dx.doi.org/10.1109/access.2019.2909068

Zhao Tianming , Tang Zijie , Zhang Tianfang , et al . Stealthy backdoor attack on RF signal classification [C ] // 2023 32nd International Conference on Computer Communications and Networks . Piscataway : IEEE , 2023 : 1 - 10 . DOI: 10.1109/icccn58024.2023.10230152 http://dx.doi.org/10.1109/icccn58024.2023.10230152

Sagduyu Y E , Erpek T , Shi Yi . Adversarial machine learning for 5G communications security [M ] // Game theory and machine learning for cyber security . New York : IEEE , 2021 : 270 - 288 . DOI: 10.1002/9781119723950.ch14 http://dx.doi.org/10.1002/9781119723950.ch14 .

Jiang Yu’e , Wang Liangmin , Chen H H , et al . Physical layer covert communication in B5G wireless networks: Its research, applications, and challenges [J ] . Proceedings of the IEEE , 2024 , 112 ( 1 ): 47 - 82 . DOI: 10.1109/jproc.2024.3364256 http://dx.doi.org/10.1109/jproc.2024.3364256

Zhao Changyuan , Du Hongyang , Niyato D , et al . Generative AI for secure physical layer communications: A survey [J ] . IEEE Transactions on Cognitive Communications and Networking , 2025 , 11 ( 1 ): 3 - 26 . DOI: 10.1109/tccn.2024.3438379 http://dx.doi.org/10.1109/tccn.2024.3438379

Davaslioglu K , Sagduyu Y E . Trojan attacks on wireless signal classification with adversarial machine learning [C ] // 2019 IEEE International Symposium on Dynamic Spectrum Access Networks . Piscataway : IEEE , 2019 : 1 - 6 . DOI: 10.1109/dyspan.2019.8935782 http://dx.doi.org/10.1109/dyspan.2019.8935782

Gan Xu , Wang Hongjun , Li Xinhao , et al . A multitarget backdoor attack against automatic modulation recognition for IoT wireless signals [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 14 ): 27588 - 27605 . DOI: 10.1109/JIOT.2025.3563204 http://dx.doi.org/10.1109/JIOT.2025.3563204

Zhao Tianya , Zhang Junqing , Mao Shiwen , et al . Explanation-guided backdoor attacks against model-agnostic RF fingerprinting systems [J ] . IEEE Transactions on Mobile Computing , 2025 , 24 ( 3 ): 2029 - 2042 . DOI: 10.1109/tmc.2024.3487967 http://dx.doi.org/10.1109/tmc.2024.3487967

Tang Zijie , Zhao Tianming , Zhang Tiandi , et al . RF domain backdoor attack on signal classification via stealthy trigger [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 12 ): 11765 - 11780 . DOI: 10.1109/tmc.2024.3404341 http://dx.doi.org/10.1109/tmc.2024.3404341

高梦楠 , 陈伟 , 吴礼发 , 等 . 面向深度学习的后门攻击及防御研究综述 [J ] . 软件学报 , 2025 , 36 ( 7 ): 3271 - 3305 .

Gao Mengnan , Chen Wei , Wu Lifa , et al . Survey on backdoor attacks and defenses for deep learning research [J ] . Journal of Software , 2025 , 36 ( 7 ): 3271 - 3305 . (in Chinese)

Chen B , Carvalho W , Baracaldo N , et al . Detecting backdoor attacks on deep neural networks by activation clustering [PP/OL ] . v1.arXiv ( 2018-11-09 )[ 2026-01-05 ] . https://arxiv.org/abs/1811.03728 https://arxiv.org/abs/1811.03728 . DOI: 10.48550/arXiv.1811.03728 http://dx.doi.org/10.48550/arXiv.1811.03728

Gao Yansong , Xu Chang , Wang Derui , et al . STRIP: A defence against Trojan attacks on deep neural networks [C ] // Proceedings of the 35th Annual Computer Security Applications Conference . New York : ACM , 2019 : 113 - 125 . DOI: 10.1145/3359789.3359790 http://dx.doi.org/10.1145/3359789.3359790

Wang Bolun , Yao Yuanshun , Shan S , et al . Neural cleanse: Identifying and mitigating backdoor attacks in neural networks [C ] // 2019 IEEE Symposium on Security and Privacy . Piscataway : IEEE , 2019 : 707 - 723 . DOI: 10.1109/sp.2019.00031 http://dx.doi.org/10.1109/sp.2019.00031

Liu Yingqi , Lee Wenchuan , Tao Guanhong , et al . ABS: Scanning neural networks for back-doors by artificial brain stimulation [C ] // Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM , 2019 : 1265 - 1282 . DOI: 10.1145/3319535.3363216 http://dx.doi.org/10.1145/3319535.3363216

Hamamreh J M , Furqan H M , Arslan H . Classifications and applications of physical layer security techniques for confidentiality: A comprehensive survey [J ] . IEEE Communications Surveys & Tutorials , 2019 , 21 ( 2 ): 1773 - 1828 . DOI: 10.1109/comst.2018.2878035 http://dx.doi.org/10.1109/comst.2018.2878035

Liu Yiliang , Chen H H , Wang Liangming . Physical layer security for next generation wireless networks: Theories, technologies, and challenges [J ] . IEEE Communications Surveys & Tutorials , 2017 , 19 ( 1 ): 347 - 376 . DOI: 10.1109/comst.2016.2598968 http://dx.doi.org/10.1109/comst.2016.2598968

West N E , O’Shea T . Deep architectures for modulation recognition [C ] // 2017 IEEE International Symposium on Dynamic Spectrum Access Networks . Piscataway : IEEE , 2017 : 1 - 6 . DOI: 10.1109/dyspan.2017.7920754 http://dx.doi.org/10.1109/dyspan.2017.7920754

Xu Jialang , Luo Chunbo , Parr G , et al . A spatiotemporal multi-channel learning framework for automatic modulation recognition [J ] . IEEE Wireless Communications Letters , 2020 , 9 ( 10 ): 1629 - 1632 . DOI: 10.1109/lwc.2020.2999453 http://dx.doi.org/10.1109/lwc.2020.2999453

Huynh-The T , Hua C H , Pham Q V , et al . MCNet: An efficient CNN architecture for robust automatic modulation classification [J ] . IEEE Communications Letters , 2020 , 24 ( 4 ): 811 - 815 . DOI: 10.1109/lcomm.2020.2968030 http://dx.doi.org/10.1109/lcomm.2020.2968030

Hermawan A P , Ginanjar R R , Kim D S , et al . CNN-based automatic modulation classification for beyond 5G communications [J ] . IEEE Communications Letters , 2020 , 24 ( 5 ): 1038 - 1041 . DOI: 10.1109/lcomm.2020.2970922 http://dx.doi.org/10.1109/lcomm.2020.2970922

Zhang Jiawei , Wang Tiantian , Feng Zhixi , et al . AMC-net: An effective network for automatic modulation classification [C ] // ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2023 : 1 - 5 . DOI: 10.1109/icassp49357.2023.10097070 http://dx.doi.org/10.1109/icassp49357.2023.10097070

Loshchilov I , Hutter F . Decoupled weight decay regularization [C ] // International Conference on Learning Representations . ICLR , 2019 . https://openreview.net/forum?id=Bkg6RiCqY7 https://openreview.net/forum?id=Bkg6RiCqY7 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进Res2Net与自适应多尺度窗口池化的调制识别方法

面向户外多声源增强的鲁棒节点特定分布式广义旁瓣对消

基于信息融合的区块链系统隐匿安全补丁识别及迁移技术

加密流量侧信道泄漏的不可避免性

基于自适应群体掩码图卷积网络的行人轨迹预测