基于深度学习的车联网无线密钥生成系统

doi:10.11959/j.issn.2096-109x.2024012

网络与信息安全学报 ›› 2024, Vol. 10 ›› Issue (1): 102-111.doi: 10.11959/j.issn.2096-109x.2024012

• 学术论文 • 上一篇

基于深度学习的车联网无线密钥生成系统

汪涵¹, 陈立全¹, 王忠民², 陆天宇¹

¹ 东南大学网络空间安全学院，江苏南京 211189
² 江苏省人民医院（南京医科大学第一附属医院），江苏南京 210029

修回日期:2023-10-08 出版日期:2024-02-01 发布日期:2024-02-01
作者简介:汪涵（1999− ），男，江苏盐城人，东南大学硕士生，主要研究方向为无线物理层密钥生成技术
陈立全（1976-），男，东南大学教授、博士生导师，主要研究方向为移动信息安全、物联网系统与安全
王忠民（1974− ），男，博士，南京医科大学教授，主要研究方向为医学信息学、医院信息系统、网络安全
陆天宇（1994− ），江苏苏州人，东南大学博士生，主要研究方向为物理层安全、无线资源分配
基金资助:
国家重点研发计划(2020YFE0200600)

Wireless key generation system for internet of vehicles based on deep learning

Han WANG¹, Liquan CHEN¹, Zhongmin WANG², Tianyu LU¹

¹ School of Cyber Science and Engineering, Southeast University, Nanjing 211189, China
² Jiangsu Province Hospital (The First Affiliated Hospital of Nanjing Medical University), Nanjing 210029, China

Revised:2023-10-08 Online:2024-02-01 Published:2024-02-01
Supported by:
The National Key R＆D Program of China(2020YFE0200600)

摘要/Abstract

摘要：

近年来，车联网技术的应用越来越广泛，并因其通信的高复杂和点对点特性备受关注。敏感而重要的车辆信息在不同的车联网设备之间传递，为了确保通信安全，有必要在合法节点之间建立安全可靠的轻量级密钥，从而对关键信息进行加密和解密。传统的密钥生成方案，在车联网中存在不灵活、不能扩展的缺陷。基于无线信道的物理层密钥生成技术因其轻量级的特性受到欢迎，并且以信息论安全性作为理论基础。在车联网环境中，设备运动速度对生成密钥的自相关性存在影响，传统的信道建模方法需要改进。同时，车联网对生成的无线密钥的随机性、一致性提出更高的要求。对基于无线物理层的密钥生成系统进行了研究，提出基于视线和多径衰落的信道建模，反映了车辆速度对自相关性的影响。提出基于累积分布函数的差分量化方法，改进了生成密钥的随机性。提出一种基于神经网络自动编码器的信息协调方案，实现可靠性和保密性的动态平衡。相较于Slepian-Wolf低密度奇偶检验码实现的方案，所提方案将比特不一致率降低30%左右。

关键词: 累积分布函数, 自动编码器, Slepian-Wolf编码, 车联网

Abstract:

In recent years, the widespread application of internet of vehicles technology has garnered attention due to its complex nature and point-to-point communication characteristics.Critical and sensitive vehicle information is transmitted between different devices in internet of vehicles, necessitating the establishment of secure and reliable lightweight keys for encryption and decryption purposes in order to ensure communication security.Traditional key generation schemes have limitations in terms of flexibility and expandability within the vehicle network.A popular alternative is the physical layer key generation technology based on wireless channels, which offers lightweight characteristics and a theoretical basis of security in information theory.However, in the context of internet of vehicles, the movement speed of devices impacts the autocorrelation of generated keys, requiring improvements to traditional channel modeling methods.Additionally, the randomness and consistency of generated wireless keys are of higher importance in applications in internet of vehicles.This research focused on a key generation system based on the wireless physical layer, conducting channel modeling based on line-of-sight and multipath fading effects to reflect the impact of vehicle speed on autocorrelation.To enhance the randomness of key generation, a differential quantization method based on cumulative distribution function was proposed.Furthermore, an information reconciliation scheme based on neural network auto-encoder was introduced to achieve a dynamic balance between reliability and confidentiality.Compared to the implementation of Slepian-Wolf low-density parity-check codes, the proposed method reduces the bit disagreement rate by approximately 30%.

Key words: cumulative distribution function, autoencoder, Slepian-Wolf coding, internet of vehicles

中图分类号:

TP309

汪涵, 陈立全, 王忠民, 陆天宇. 基于深度学习的车联网无线密钥生成系统[J]. 网络与信息安全学报, 2024, 10(1): 102-111.

Han WANG, Liquan CHEN, Zhongmin WANG, Tianyu LU. Wireless key generation system for internet of vehicles based on deep learning[J]. Chinese Journal of Network and Information Security, 2024, 10(1): 102-111.

图/表 10

图1

图2

图3

图4

图5

图6

表1

图7

图8

图9

参考文献 18

[1]	SHAWKY M A , USMAN M , IMRAN M A ,et al. Adaptive chaotic map-based key extraction for efficient cross-layer authentication in VANETs[J]. Vehicular Communications. 2023,39: 4-5.
[2]	CHENG L , STANCIL D D , BAI F ,et al. A roadside scattering model for the vehicle-to-vehicle communication channel[J]. IEEE Journal on Selected Areas in Communications, 2013,31(9): 449-459.
[3]	MARGELIS G , FAFOUTIS X , OIKONOMOU G ,et al. Physical layer secret-key generation with discreet cosine transform for the Internet of Things[C]// Proceedings of IEEE International Conference on Communications (ICC). 2017: 2-4.
[4]	YANG H Q , LIU H B , LUO C W ,et al. Vehicle-key:a secret key establishment scheme for LoRa-enabled IoV communications[C]// Proceedings of IEEE 42nd International Conference on Distributed Computing Systems. 2022: 5-7.
[5]	LI K , LU L Y , NI W ,et al. Secret key agreement for data dissemination in vehicular platoons[J]. IEEE Transactions on Vehicular Technology, 2019,99:1.
[6]	LI S , MA Y F , GU X ,et al. Wi-Fi-based device-free vehicle speed measurement using fast phase correction MUSIC algorithm[C]// Proceedings of 2020 International Conferences on Internet of Things (iThings). 2020: 9060-9062.
[7]	LIU H , WANG Y , REN Y ,et al. Bipartite graph matching based secret key generation[C]// Proceedings of IEEE Conference on Computer Communications. 2021.
[8]	ZHANG J Q , MARSHALL A , WOODS R ,et al. Efficient key generation by exploiting randomness from channel responses of individual OFDM subcarriers[J]. IEEE Transactions on Communications, 2016,64(6): 2579-2580.
[9]	PAN Y J , XU Z Q , LI M ,et al. Man-in-the-middle attack resistant secret key generation via channel randomization[C]// Proceedings of International Symposium on Mobile Ad Hoc Networking and Computing. 2021: 231-240.
[10]	ERCEG V , SCHUMACHER L , KYRITSI P ,et al. TGn channel models[S]. IEEE Standard 802.11-03/940r4, 2004.
[11]	ZHANG J Q , LI G Y , MARSHALL A ,et al. A new frontier for loT security emerging from three decades of key generation relying on wireless channels[J]. IEEE Access, 2020,8(99): 138410-138412.
[12]	BAKSI S , SNOAP J , POPESCU D C . Secret key generation using one-bit quantized channel state information[C]// Proceedings of Wireless Communications Networking Conference. 2017.
[13]	RANA V , CHOU R A . Design of short block length wiretap channel codes:deep learning and cryptography working hand in hand[C]// Proceedings of IEEE Information Theory Workshop (ITW). 2021.
[14]	LIN Q , XU W T , LIU J ,et al. H2b:heartbeat-based secret key generation using piezo vibration sensors[C]// Proceedings of the Inter- national Conference on Information Processing in Sensor Networks(IPSN). 2019: 265-267.
[15]	BESSER K L , LIN P H , JANDA C R ,et al. Wiretap code design by neural network autoencoders[J]. IEEE Transactions on Information Forensics and Security. 2019,5(99): 3377-3378.
[16]	ARTEMY K , BRENDAN T . Estimating mixture entropy with pairwise distances[J]. Entropy, 2017,19(7): 361-362.
[17]	李默, 张春梅, 银振强 ,等. 量子密钥分配后处理概述[J]. 密码学报, 2015(2): 9.
	LI M , ZHANG C M , YIN Z Q ,et al. Overview of post-processing for quantum key distribution[J]. Journal of Cryptologic Research, 2015(2): 9.
[18]	杨铮, 刘云浩 . Wi-Fi雷达:从RSSI到CSI[J]. 中国计算机协会通讯, 2014,10(11): 55-57.
	YANG Z , LIU Y H . Wi-Fi radar:from RSSI to CSI[J]. Communications of the China Computer Federation, 2014,10(11): 55-57.

随机性测试	二元矩阵秩检验测试值	二元矩阵秩检验测通过情况重叠模块匹配检验测试值	重叠模块匹配检验通过情况	线性复杂度检验测试值	线性复杂度检验通过情况	随机游动检验测试值	随机游动检验通过情况	随机游动状态频率检验测试值	随机游动状态频率检验通过情况
单门限量化	2.338×10^-6	不通过 0.000 2	不通过	1.360×10^-37	不通过	0.699 9	通过	0.617	通过
基于累积分布函数的值域量化	2.338×10^-6	不通过 0.000 18	不通过	1.5247×10^-8	不通过	0.776 5	通过	1	通过
基于累积分布函数的差分量化	0.413 5	通过0.126 1	通过	0.410 8	通过	0.849 1	通过	1	通过

基于深度学习的车联网无线密钥生成系统

Wireless key generation system for internet of vehicles based on deep learning

在线阅读

pdf下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 18

相关文章 8

Metrics

推荐阅读 0

[1]	何智旺, 王化群. 面向车联网的匿名组密钥分发方案[J]. 网络与信息安全学报, 2023, 9(5): 127-137.
[2]	易杰, 曹腾飞, 郜帅, 黄建强. 车联网中基于攻防博弈的蜜罐防御及传输策略[J]. 网络与信息安全学报, 2022, 8(4): 157-167.
[3]	翟宝琴, 王健, 韩磊, 刘吉强, 何嘉豪, 刘天皓. 基于信任值的车联网分层共识优化协议[J]. 网络与信息安全学报, 2022, 8(3): 142-153.
[4]	徐堂炜,张海璐,刘楚环,肖亮,朱珍民. 基于强化学习的低时延车联网群密钥分配管理技术[J]. 网络与信息安全学报, 2020, 6(5): 119-125.
[5]	王瑞锦,唐榆程,张巍琦,张凤荔. 基于同态加密和区块链技术的车联网隐私保护方案[J]. 网络与信息安全学报, 2020, 6(1): 46-53.
[6]	赵子文,叶阿勇,金俊林,孟玲玉. 基于车辆协作的混淆路径轨迹隐私保护机制[J]. 网络与信息安全学报, 2019, 5(4): 52-62.
[7]	王良民,刘晓龙,李春晓,杨睛,杨卫东. 5G车联网展望[J]. 网络与信息安全学报, 2016, 2(6): 1-12.
[8]	王良民,李婷婷,陈龙. 基于车辆身份的车联网结构与安全[J]. 网络与信息安全学报, 2016, 2(2): 41-54.