基于轻量化DCGAN的通信干扰生成技术

doi:10.3969/j.issn.1009-086x.2026.03.013

摘要/Abstract

摘要：

传统的干扰波形生成方法需要提前获取目标信号的参数特征，在面对如今复杂多样的通信信号样式时难以取得良好的效果。针对这个问题，提出一种基于轻量化深层卷积生成对抗网络（deep convolution generative adversarial networks，DCGAN）的通信干扰生成技术。利用DCGAN网络在无先验信息条件下无监督学习目标信号特征，生成与目标信号高度相似的干扰波形。同时对网络进行了轻量化处理，减少了网络参数量。针对多种调制类型的通信信号进行了仿真实验，实验结果表明：轻量化DCGAN网络在参数量减少了约38%的情况下，生成的干扰波形质量并未下降。在0 dB干信比（jamming-to-signal ratio, JSR）以上时，受生成干扰波形影响的通信系统的误比特率（bit error ratio, BER）快速逼近0.5，远优于传统干扰波形的干扰效果。

关键词: 通信干扰, 干扰生成, 机器学习, 深层卷积生成对抗网络, 轻量化网络

Abstract:

Traditional interference waveform generation methods require prior acquisition of parameter characteristics of the target signal， making it difficult to achieve favorable results when confronted with the complex and diverse communication signal patterns nowadays. To address this issue， this paper proposes a communication interference generation technology based on lightweight deep convolutional generative adversarial networks （DCGAN）. The DCGAN network is utilized to perform unsupervised learning on the features of the target signal without prior information， thereby generating interference waveforms that are highly similar to the target signal. Meanwhile， lightweight processing is applied to the network to reduce the number of network parameters. In this paper， simulation experiments are conducted on communication signals of various modulation types. The experimental results show that the lightweight DCGAN network reduces the number of parameters by approximately 38% without compromising the quality of the generated interference waveforms. When the jamming-to-signal ratio （JSR） is above 0 dB， the bit error ratio （BER） of the communication system affected by the generated interference waveforms rapidly approaches 0.5， which is far superior to the interference effect of traditional interference waveforms.

Key words: communication interference, interference generation, machine learning, deep convolutional generative adversarial network, lightweight network

中图分类号:

TN975

潘黎, 阮航, 付亦凡, 周东平, 雷蕾. 基于轻量化DCGAN的通信干扰生成技术[J]. 现代防御技术, 2026, 54(3): 140-150.

Li PAN, Hang RUAN, Yifan FU, Dongping ZHOU, Lei LEI. Communication Interference Generation Technology Based on Lightweight DCGAN[J]. Modern Defense Technology, 2026, 54(3): 140-150.

图/表 14

图1 16QAM信号的星座图

Fig. 1 Constellation diagram of 16QAM signal

图2 通信信号时域波形

Fig. 2 Time-domain waveform of communication signals

图3 DCGAN基本结构

Fig. 3 Basic structure of DCGAN

图4 DCGAN网络结构

Fig. 4 DCGAN network architecture

表1 判别网络的卷积层参数

Table 1 Convolutional layer parameters of the discriminator

卷积层序号	特征维度	卷积核宽度
Conv1	32	13
Conv2	64	11
Conv3	128	9
Conv4	256	7
Conv5	1	4

表2 生成网络的卷积层参数

Table 2 Convolutional layer parameters of the generator

转置卷积层序号	特征维度	卷积核宽度
Tconv1	512	5
Tconv2	256	7
Tconv3	128	9
Tconv4	64	11
Tconv5	2	13

表3 网络参数量对比

Table 3 Comparison of network parameters

网络类型	网络参数总量
轻量化DCGAN网络	1 739 497
全大核DCGAN网络	2 808 955

图6 算法流程

Fig. 6 Algorithm procedure

图7 DCGAN网络训练损失函数

Fig. 7 DCGAN training loss function

图8 信号星座图对比

Fig. 8 Constellation diagram comparison

图9 4FSK频谱图对比

Fig. 9 4FSK spectrogram comparison

图10 调制分类网络训练损失函数与分类准确率

Fig. 10 Modulation classification network training loss function and classification accuracy

表4 调制分类结果

Table 4 Modulation classification results

调制类型	分类为对应类型的比率/%
QPSK	97.40
16QAM	100
4FSK	100

图11 5种干扰下通信系统的BER

Fig. 11 BER of communication systems interfered by five kinds of interference

参考文献 27

[1]	SHARMA P， SARMA K K， MASTORAKIS N E. Artificial Intelligence Aided Electronic Warfare Systems-Recent Trends and Evolving Applications［J］. IEEE Access， 2020， 8： 224761-224780.
[2]	ALREFAEI F， ALZAHRANI A， SONG Houbing， et al. A Survey on the Jamming and Spoofing Attacks on the Unmanned Aerial Vehicle Networks［C］∥2022 IEEE International IOT， Electronics and Mechatronics Conference （IEMTRONICS）. Piscataway： IEEE， 2022： 1-7.
[3]	LUO Zhaoyi， DENG Min， YAO Zhiqiang， et al. Distributed Blanket Jamming Resource Scheduling for Satellite Navigation Based on Particle Swarm Optimization and Genetic Algorithm［C］∥2020 IEEE 20th International Conference on Communication Technology （ICCT）. Piscataway： IEEE， 2020： 611-616.
[4]	邓敏，伍志高，姚志强，等. 带精英集并行遗传算法的无人机干扰资源调度［J］. 电子与信息学报， 2022， 44（6）： 2158-2165.
	DENG Min， WU Zhigao， YAO Zhiqiang， et al. Unmanned Aerial Vehicle Jamming Resource Scheduling Based on Parallel Genetic Algorithm with Elite Set［J］. Journal of Electronics & Information Technology， 2022， 44（6）： 2158-2165.
[5]	THANH P D， GIANG H T H， HONG I P. Anti-Jamming RIS Communications Using DQN-Based Algorithm［J］. IEEE Access， 2022， 10： 28422-28433.
[6]	ZHANG Chudi， WANG Lei， JIANG Rundong， et al. Radar Jamming Decision-Making in Cognitive Electronic Warfare： A Review［J］. IEEE Sensors Journal， 2023， 23（11）： 11383-11403.
[7]	JIA Luliang， QI Nan， CHU Feihuang， et al. Game-Theoretic Learning Anti-jamming Approaches in Wireless Networks［J］. IEEE Communications Magazine， 2022， 60（5）： 60-66.
[8]	LI Yongcheng， MIAO Weijian， GAO Zhenzhen， et al. Intelligent Jamming Strategy for Wireless Communications Based on Game Theory［J］. IEEE Access， 2024， 12： 110064-110077.
[9]	赵凡，金虎. 基于GAN的通信干扰波形生成技术［J］. 系统工程与电子技术， 2021， 43（4）： 1080-1088.
	ZHAO Fan， JIN Hu. Communication Jamming Waveform Generation Technology Based on GAN［J］. Systems Engineering and Electronics， 2021， 43（4）： 1080-1088.
[10]	GOODFELLOW I J， POUGET-ABADIE J， MIRZA M， et al. Generative Adversarial Nets［C］∥Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge： MIT Press， 2014： 2672-2680.
[11]	GOODFELLOW I， POUGET-ABADIE J， MIRZA M， et al. Generative Adversarial Networks［J］. Communications of the ACM， 2020， 63（11）： 139-144.
[12]	RADFORD A， METZ L， CHINTALA S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks［EB/OL］. （2016-01-07）［2025-05-09］. .
[13]	ÖCAL A， ÖZBAKIR L. Supervised Deep Convolutional Generative Adversarial Networks［J］. Neurocomputing， 2021， 449： 389-398.
[14]	BAHMEI B， BIRMINGHAM E， ARZANPOUR S. CNN-RNN and Data Augmentation Using Deep Convolutional Generative Adversarial Network for Environmental Sound Classification［J］. IEEE Signal Processing Letters， 2022， 29： 682-686.
[15]	付亦凡，阮航，周东平，等. 基于改进轻量化神经网络的干扰识别方法［J］. 现代防御技术， 2025， 53（2）： 91-98.
	FU Yifan， RUAN Hang， ZHOU Dongping， et al. Radar Interference Recognition Based on Improved Lightweight Convolutional Neural Networks［J］. Modern Defence Technology， 2025， 53（2）： 91-98.
[16]	FENG Xi， HU Jianwen， WU Wanneng， et al. Dynamic Large-Small Kernel Convolutional Neural Network for Pansharpening［J］. IEEE Geoscience and Remote Sensing Letters， 2023， 20： 1-5.
[17]	SEGU M， TONIONI A， TOMBARI F. Batch Normalization Embeddings for Deep Domain Generalization［J］. Pattern Recognition， 2023， 135： 109115.
[18]	LIU Bingqi， Jiwei LÜ， FAN Xinyue， et al. Application of an Improved DCGAN for Image Generation［J］. Mobile Information Systems， 2022， 2022（1）： 9005552.
[19]	DEWI C， CHEN R C， LIU Yanting， et al. Synthetic Data Generation Using DCGAN for Improved Traffic Sign Recognition［J］. Neural Computing and Applications， 2022， 34（24）： 21465-21480.
[20]	GARBIN C， ZHU Xingquan， MARQUES O. Dropout vs. Batch Normalization： An Empirical Study of Their Impact to Deep Learning［J］. Multimedia Tools and Applications， 2020， 79（19）： 12777-12815.
[21]	GUI Jie， SUN Zhenan， WEN Yonggang， et al. A Review on Generative Adversarial Networks： Algorithms， Theory， and Applications［J］. IEEE Transactions on Knowledge and Data Engineering， 2023， 35（4）： 3313-3332.
[22]	SOYDANER D. A Comparison of Optimization Algorithms for Deep Learning［J］. International Journal of Pattern Recognition and Artificial Intelligence， 2020， 34（13）： 2052013.
[23]	YI D， AHN J， JI S. An Effective Optimization Method for Machine Learning Based on Adam［J］. Applied Sciences， 2020， 10（3）： 1073.
[24]	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.
[25]	O’SHEA T J， ROY T， CLANCY T C. Over-the-Air Deep Learning Based Radio Signal Classification［J］. IEEE Journal of Selected Topics in Signal Processing， 2018， 12（1）： 168-179.
[26]	LIU Xiaoyu， YANG Diyu， GAMAL A E. Deep Neural Network Architectures for Modulation Classification［C］∥2017 51st Asilomar Conference on Signals， Systems， and Computers. Piscataway， NJ， USA： IEEE， 2017： 915-919.
[27]	牛朝阳，王建涛，胡涛，等. 极化合成孔径雷达有源干扰的干信比方程［J］. 系统工程与电子技术， 2021， 43（12）： 3542-3551.
	NIU Zhaoyang， WANG Jiantao， HU Tao， et al. Interference Signal Ratio Equation of Polarimetric Synthetic Aperture Radar Active Jamming［J］. Systems Engineering and Electronics， 2021， 43（12）： 3542-3551.