面向智能无人通信系统的因果性对抗攻击生成算法

doi:10.11959/j.issn.1000-436x.2024036

通信学报 ›› 2024, Vol. 45 ›› Issue (1): 54-62.doi: 10.11959/j.issn.1000-436x.2024036

• 专题：面向有人无人协同的智能通信与组网技术 • 上一篇

面向智能无人通信系统的因果性对抗攻击生成算法

禹树文¹, 许威¹^,², 姚嘉铖¹

¹ 东南大学移动通信全国重点实验室，江苏南京 210096
² 网络通信与安全紫金山实验室，江苏南京 211111

修回日期:2023-08-28 出版日期:2024-01-01 发布日期:2024-01-01
作者简介:禹树文（1996- ），男，蒙古族，江苏盐城人，东南大学博士生，主要研究方向为智能通信、通感一体化
许威（1982- ），男，江苏如皋人，博士，东南大学教授、博士生导师，主要研究方向为无线通信、智能通信等
姚嘉铖（1999- ），男，江苏如东人，东南大学博士生，主要研究方向为无线分布式智能
基金资助:
国家自然科学基金资助项目(62022026);国家自然科学基金资助项目(62211530108);中央高校基本科研业务费专项资金资助项目(2242022K60002);中央高校基本科研业务费专项资金资助项目(2242023K5003)

Causality adversarial attack generation algorithm for intelligent unmanned communication system

Shuwen YU¹, Wei XU¹^,², Jiacheng YAO¹

¹ National Mobile Communications Research Laboratory, Southeast University, Nanjing 210096, China
² Purple Mountain Laboratories, Nanjing 211111, China

Revised:2023-08-28 Online:2024-01-01 Published:2024-01-01
Supported by:
The National Natural Science Foundation of China(62022026);The National Natural Science Foundation of China(62211530108);The Fundamental Research Funds for the Central Universities(2242022K60002);The Fundamental Research Funds for the Central Universities(2242023K5003)

摘要/Abstract

摘要：

考虑到基于梯度的对抗攻击生成算法在实际通信系统部署中面临着因果性问题，提出了一种因果性对抗攻击生成算法。利用长短期记忆网络的序列输入输出特征与时序记忆能力，在满足实际应用中存在的因果性约束前提下，有效提取通信信号的时序相关性，增强针对无人通信系统的对抗攻击性能。仿真结果表明，所提算法在同等条件下的攻击性能优于泛用对抗扰动等现有的因果性对抗攻击生成算法。

关键词: 智能通信系统, 对抗攻击, 深度学习, 因果系统, 长短期记忆网络

Abstract:

A causality adversarial attack generation algorithm was proposed in response to the causality issue of gradient-based adversarial attack generation algorithms in practical communication system.The sequential input-output features and temporal memory capability of long short-term memory networks were utilized to extract the temporal correlation of communication signals while satisfying practical causality constraints, and enhance the adversarial attack performance against unmanned communication systems.Simulation results demonstrate that the proposed algorithm outperforms existing causality adversarial attack algorithms, such as universal adversarial perturbation, under identical conditions.

Key words: intelligent communication system, adversarial attack, deep learning, causal system, long short-term memory network

中图分类号:

TN911

禹树文, 许威, 姚嘉铖. 面向智能无人通信系统的因果性对抗攻击生成算法[J]. 通信学报, 2024, 45(1): 54-62.

Shuwen YU, Wei XU, Jiacheng YAO. Causality adversarial attack generation algorithm for intelligent unmanned communication system[J]. Journal on Communications, 2024, 45(1): 54-62.

图/表 9

图1

图2

图3

图4

表1

BIM算法的迭代次数与迭代步长"

JNR/dB	迭代次数	迭代步长
-30	1	$ϵ_{- 30 dB}$
-26	1	$0.8 ϵ_{- 26 dB}$
-22	1	$ϵ_{- 22 dB}$
-18	3	$ϵ_{- 18 dB}$
-14	18	$0.2 ϵ_{- 14 dB}$
-10	20	$0.3 ϵ_{- 10 dB}$
-6	20	$0.5 ϵ_{- 6 dB}$
-2	17	$0.7 ϵ_{- 2 dB}$
2	19	$0.7 ϵ_{2 dB}$
6	18	$0.9 ϵ_{6 dB}$

表1

图5

图6

图7

图8

参考文献 25

[1]	YOU X H , WANG C X , HUANG J ,et al. Towards 6G wireless communication networks:vision,enabling technologies,and new paradigm shifts[J]. Science China Information Sciences, 2020,64(1): 1-74.
[2]	XU W , HUANG Y M , WANG W ,et al. Toward ubiquitous and intelligent 6G networks:from architecture to technology[J]. Science China Information Sciences, 2023,66(3): 1-2.
[3]	XU W , YANG Z H , NG D W K ,et al. Edge learning for B5G networks with distributed signal processing:semantic communication,edge computing,and wireless sensing[J]. IEEE Journal of Selected Topics in Signal Processing, 2023,17(1): 9-39.
[4]	YAO J C , YANG Z H , XU W ,et al. GoMORE:global model reuse for resource-constrained wireless federated learning[J]. IEEE Wireless Communications Letters, 2023,12(9): 1543-1547.
[5]	WEI K , XU J D , XU W ,et al. Distributed neural precoding for hybrid mmWave MIMO communications with limited feedback[J]. IEEE Communications Letters, 2022,26(7): 1568-1572.
[6]	XIA W C , ZHENG G , ZHU Y X ,et al. A deep learning framework for optimization of MISO downlink beamforming[J]. IEEE Transactions on Communications, 2020,68(3): 1866-1880.
[7]	SHI W , XU W , YOU X H ,et al. Intelligent reflection enabling technologies for integrated and green internet-of-everything beyond 5G:communication,sensing,and security[J]. IEEE Wireless Communications, 2023,30(2): 147-154.
[8]	XIE R J , XU W , YU J B ,et al. Disentangled representation learning for RF fingerprint extraction under unknown channel statistics[J]. IEEE Transactions on Communications, 2023,71(7): 3946-3962.
[9]	QI Q , WANG J Y , MA Z Y ,et al. Knowledge-driven service offloading decision for vehicular edge computing:a deep reinforcement learning approach[J]. IEEE Transactions on Vehicular Technology, 2019,68(5): 4192-4203.
[10]	HUANG K , LUO Z Z , LIANG L ,et al. Fast spectrum sharing in vehicular networks:a meta reinforcement learning approach[C]// Proceedings of the IEEE 96th Vehicular Technology Conference (VTC2022-Fall). Piscataway:IEEE Press, 2022: 1-5.
[11]	陈杰, 辛斌 . 有人/无人系统自主协同的关键科学问题[J]. 中国科学:信息科学, 2018,48(9): 1270-1274.
	CHEN J , XIN B . Key scientific problems in the autonomous cooperation of manned-unmanned systems[J]. Scientia Sinica (Informationis), 2018,48(9): 1270-1274.
[12]	SZEGEDY C , ZAREMBA W , SUTSKEVER I ,et al. Intriguing properties of neural networks[J]. arXiv Preprint,arXiv:1312.6199, 2013.
[13]	YAO J C , YANG Z H , XU W ,et al. Imperfect CSI:a key factor of uncertainty to over-the-air federated learning[J]. IEEE Wireless Communications Letters, 2023,12(12): 2273-2277.
[14]	GOODFELLOW I J , SHLENS J , SZEGEDY C . Explaining and harnessing adversarial examples[J]. arXiv Preprint,arXiv:1412.6572, 2014.
[15]	KURAKIN A , GOODFELLOW I J , BENGIO S . Adversarial machine learning at scale[J]. arXiv Preprint,arXiv:1611.01236, 2016.
[16]	MOOSAVI-DEZFOOLI S M , FAWZI A , FAWZI O ,et al. Universal adversarial perturbations[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2017: 86-94.
[17]	SADEGHI M , LARSSON E G . Adversarial attacks on deep-learning based radio signal classification[J]. IEEE Wireless Communications Letters, 2019,8(1): 213-216.
[18]	KIM B , SAGDUYU Y E , DAVASLIOGLU K ,et al. Channel-aware adversarial attacks against deep learning-based wireless signal classifiers[J]. IEEE Transactions on Wireless Communications, 2022,21(6): 3868-3880.
[19]	MANOJ B R , SADEGHI M , LARSSON E G . Downlink power allocation in massive MIMO via deep learning:adversarial attacks and training[J]. IEEE Transactions on Cognitive Communications and Networking, 2022,8(2): 707-719.
[20]	LIU Q , GUO J J , WEN C K ,et al. Adversarial attack on DL-based massive MIMO CSI feedback[J]. Journal of Communications and Networks, 2020,22(3): 230-235.
[21]	TIAN J J , PEI Y Y , HUANG Y D ,et al. Modulation-constrained clustering approach to blind modulation classification for MIMO systems[J]. IEEE Transactions on Cognitive Communications and Networking, 2018,4(4): 894-907.
[22]	O’SHEA T , WEST N E . Radio machine learning dataset generation with GNU radio[C]// Proceedings of the GNU Radio Conference.[S.l.:s.n.], 2016: 69-74.
[23]	HOCHREITER S , SCHMIDHUBER J . Long short-term memory[J]. Neural Computation, 1997,9(8): 1735-1780.
[24]	GERS F A , SCHMIDHUBER J , CUMMINS F . Learning to forget:continual prediction with LSTM[J]. Neural Computation, 2000,12(10): 2451-2471.
[25]	LI D , CHEN D C , SHI L ,et al. MAD-GAN:multivariate anomaly detection for time series data with generative adversarial networks[C]// Proceedings of 28th International Conference on Atificial Neural Networks (ICANN). Berlin:Springer, 2019: 703-716.

面向智能无人通信系统的因果性对抗攻击生成算法

Causality adversarial attack generation algorithm for intelligent unmanned communication system

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 25

相关文章 15

Metrics

推荐阅读 0

[1]	张学军, 张奉鹤, 盖继扬, 杜晓刚, 周文杰, 蔡特立, 赵博. mVulSniffer：一种多类型源代码漏洞检测方法[J]. 通信学报, 2023, 44(9): 149-160.
[2]	李勉, 李洋, 张纵辉, 史清江. Massive MIMO中通信高效的分布式预编码设计[J]. 通信学报, 2023, 44(8): 37-48.
[3]	陈晓霖, 昝道广, 吴炳潮, 关贝, 王永吉. 面向纵向联邦学习的对抗样本生成算法[J]. 通信学报, 2023, 44(8): 1-13.
[4]	王慧娇, 张鑫, 韦永壮, 李灵琛. 基于深度学习的SM4密码算法新型区分器[J]. 通信学报, 2023, 44(7): 171-184.
[5]	马帅, 裴科, 祁华艳, 李航, 曹雯, 王洪梅, 熊海良, 李世银. 基于生成模型的地磁室内高精度定位算法研究[J]. 通信学报, 2023, 44(6): 211-222.
[6]	李荣鹏, 汪丙炎, 张宏纲, 赵志峰. 知识增强的语义通信接收端设计[J]. 通信学报, 2023, 44(6): 70-76.
[7]	陈东昱, 陈华, 范丽敏, 付一方, 王舰. 基于深度学习的随机性检验策略研究[J]. 通信学报, 2023, 44(6): 23-33.
[8]	张昀, 周婧, 黄经纬, 于舒娟, 黄丽亚. 基于深度学习的正交频分复用系统信道估计[J]. 通信学报, 2023, 44(12): 124-133.
[9]	汪欣欣, 陈晶, 何琨, 张子君, 杜瑞颖, 李瞧, 佘计思. 面向目标检测的对抗攻击与防御综述[J]. 通信学报, 2023, 44(11): 260-277.
[10]	谢刚, 王荃毅, 谢新林, 王健安. 融合多尺度深度卷积的轻量级Transformer交通场景语义分割算法[J]. 通信学报, 2023, 44(10): 213-225.
[11]	杨洁, 董标, 付雪, 王禹, 桂冠. 基于轻量化分布式学习的自动调制分类方法[J]. 通信学报, 2022, 43(7): 134-142.
[12]	杨秀璋, 彭国军, 李子川, 吕杨琦, 刘思德, 李晨光. 基于Bert和BiLSTM-CRF的APT攻击实体识别及对齐研究[J]. 通信学报, 2022, 43(6): 58-70.
[13]	廖育荣, 王海宁, 林存宝, 李阳, 方宇强, 倪淑燕. 基于深度学习的光学遥感图像目标检测研究进展[J]. 通信学报, 2022, 43(5): 190-203.
[14]	廖勇, 王世义. 高速移动环境下基于RM-Net的大规模MIMO CSI反馈算法[J]. 通信学报, 2022, 43(5): 166-176.
[15]	赵增华, 童跃凡, 崔佳洋. 基于域自适应的Wi-Fi指纹设备无关室内定位模型[J]. 通信学报, 2022, 43(4): 143-153.