西安电子科技大学学报 ›› 2024, Vol. 51 ›› Issue (6): 194-203.doi: 10.19665/j.issn1001-2400.20230605

• 计算机科学与技术 & 网络空间安全 • 上一篇    下一篇

机器学习辅助的车联网紧急消息信任评估方案

周浩1(), 邵诗韵2(), 马勇3(), 刘志全1,4(), 官全龙1(), 王晓明1()   

  1. 1.暨南大学 网络空间安全学院,广东 广州 510632
    2.电子科技大学 计算机科学与工程学院,四川 成都 611731
    3.江西师范大学 计算机信息工程学院,江西 南昌 330022
    4.数力聚(北京)科技有限公司,北京 100020
  • 收稿日期:2023-05-07 出版日期:2024-12-20 发布日期:2024-12-05
  • 通讯作者: 邵诗韵(1996—),女,电子科技大学博士研究生,E-mail:shaokcl@gmail.com
  • 作者简介:周 浩(1996—),男,暨南大学硕士研究生,E-mail:lzyhaozhou@163.com;
    马 勇(1977—),男,教授,E-mail:may@jxnu.edu.cn;
    刘志全(1989—),男,教授,E-mail:zqliu@vip.qq.com;
    官全龙(1981—),男,教授,E-mail:gql@jnu.edu.cn;
    王晓明(1960—),女,教授,E-mail: twxm@jnu.edu.cn
  • 基金资助:
    国家自然科学基金(61932010);国家自然科学基金(62441211);国家自然科学基金(62272195);广东省基础与应用基础研究基金(2024A1515012776);广东省基础与应用基础研究基金(2022A1515010760);广东省重点研发计划项目(2020B0909030005);广东省重点研发计划项目(2020B1212030003);广东省市场监督管理局科技项目(2023ZZ03);广州市科技计划项目(202201010422);广州市科技计划项目(202201010421);中央高校基本科研业务费专项资金(21622402);国家市场监管重点实验室(智能机器人安全)开放课题(GQI-KFKT202205)

Machine learning-assisted trust evaluation scheme for emergency messages in VANETs

ZHOU Hao1(), SHAO Shiyun2(), MA Yong3(), LIU Zhiquan1,4(), GUAN Quanlong1(), WANG Xiaoming1()   

  1. 1. College of Cyber Security,Jinan University,Guangzhou 510632,China
    2. School of Computer Science & Engineering,University of Electronic Science and Technology of China, Chengdu 611731,China
    3. School of Computer and Information Engineering,Jiangxi Normal University,Nanchang 330022,China
    4. Cyberdataforce(Beijing) Technology Ltd.,Beijing 100020,China
  • Received:2023-05-07 Online:2024-12-20 Published:2024-12-05

摘要:

车联网是智能交通系统的重要组成部分,能够通过传播车辆消息提高交通安全和效率,近年来得到政府、工业和学术界的广泛研究。然而,在车联网中,恶意车辆广播的虚假紧急消息将对车联网正常运行和交通安全造成极大的威胁。为解决现有车联网信任管理方案在高恶意车辆占比下消息信任评估准确性低的问题,提出一种车联网中机器学习辅助的紧急消息信任评估方案。提出的方案对现有方案的消息信任评估算法进行优化,在评估过程中引入随机森林模型以辅助路侧单元对车联网中紧急消息进行分析,并输出消息为真实消息的预测概率;接着,基于随机森林模型输出的预测概率设计可切换缓存机制,并结合智能合约设计信任值查询算法,以平衡现有方案中路侧单元在查询效率和存储空间开销之间的冲突;同时,将预测概率作为参考因子引入消息信任评估算法,以得到更高的消息评估准确率;最后,基于所提方案,与现有方案进行对比。实验结果表明,所提方案的消息信任评估准确率提升约6.2%~21.9%,且在多种恶意车辆占比下表现出较好的鲁棒性。

关键词: 车联网, 紧急消息, 机器学习, 智能合约, 信任评估

Abstract:

Vehicular ad hoc networks(VANETs) are an important part of intelligent transportation systems and can improve traffic safety and efficiency through the dissemination of vehicle messages.However,the dissemination of false emergency messages by malicious vehicles poses a serious threat to the normal operation of VANETs and traffic safety.To address the low accuracy of message trust evaluation in existing trust management schemes for VANETs with a high proportion of malicious vehicles,a machine learning-assisted trust evaluation scheme is proposed which optimizes the existing trust evaluation algorithm by introducing a random forest model to assist roadside units in analyzing emergency messages and outputting the prediction probability of messages being true.Based on the prediction probability output by the random forest model,a switchable caching mechanism is designed,and a trust value query algorithm is designed to balance the conflict between query efficiency and storage space overhead of roadside units in the existing scheme.Meanwhile,the prediction probability is used as a reference factor in the trust evaluation algorithm to obtain a higher message evaluation accuracy.Finally,the proposed scheme is compared with the existing scheme,and experimental results show that the message trust evaluation accuracy of the proposed scheme is improved by approximately 6.2%~21.9% and that the proposed scheme exhibits good robustness under several proportions of malicious vehicles.

Key words: vehicular ad-hoc networks, emergency message, machine learning, smart contract, trust evaluation

中图分类号: 

  • TP309