基于单分类支持向量机的CAN总线异常检测方法Abnormity Detection Method for In-Vehicle CAN Bus Based on One-Class SVM
盛铭;陈凌珊;汪俊杰;杜红亮;
摘要(Abstract)：
为提高智能客车的网络安全性,提出一种基于单分类支持向量机模型的CAN总线报文异常检测方法,根据智能客车CAN总线的报文数据域特性,分析攻击对数据域产生的影响,将CAN报文的数据域提取成8个训练特征,以大量的行驶数据作为训练集和测试集,通过随机和仿真方式生成异常数据,采用交叉验证的方式对参数进行调整。试验结果表明,该模型能有效检测出异常数据,提升了智能客车的行驶安全性。
关键词(KeyWords)： 车联网;车载CAN总线;异常检测;单分类支持向量机
基金项目(Foundation):
作者(Authors): 盛铭;陈凌珊;汪俊杰;杜红亮;
DOI: 10.19620/j.cnki.1000-3703.20190382
参考文献(References)：
- [1]MILLER C,VALASEK C.Remote Exploitation of an Unaltered Passenger Vehicle[R].IOActive,2015.
- [2]于赫.网联汽车信息安全问题及CAN总线异常检测技术研究[D].长春:吉林大学,2016.
- [3]TAYLOR A,LEBLANC S,JAPKOWICZ N.Anomaly Detection in Automobile Control Network Data with Long Short-Term Memory Networks[C]//2016 IEEE International Conference on Data Science and Advanced Analytics(DSAA).IEEE,2016:130-139.
- [4]MARCHETTI M,STABLI D.Anomaly Detection of CANBus Messages through Analysis of ID Sequences[C]//2017IEEE Intelligent Vehicles Symposium(IV).IEEE,2017.
- [5]THEISSLER A.Detecting Known and Unknown Faults in Automotive Systems Using Ensemble-Based Anomaly Detection[J].Knowledge-Based Systems,2017,123:163-173.
- [6]杨宏.基于智能网联汽车的CAN总线攻击与防御检测技术研究[D].天津:天津理工大学,2017.
- [7]JI H N,WANG Y,QIN H,et al.Comparative Performance Evaluation of Intrusion Detection Methods for In-Vehicle Networks[J].IEEE Access,2018,6:37523-37532.
- [8]WANG C,ZHAO Z,GONG L,et al.A Distributed Anomaly Detection System for in-Vehicle Network Using HTM[J].IEEE Access,2018,6:9091-9098.
- [9]SCHOLKOPF B,WILLIAMSON R C,SMOLA A J,et al.Support Vector Method for Novelty Detection[C]//Advances in Neural Information Processing Systems.2000:582-588.
- [10]SCHOLKOPF B,PLATT J C,SHAWE-TAYLORJ,et al.Estimating the Support of a High-Dimensional Distribution[J].Neural computation,2001,13(7):1443-1471.
- [11]XIAO Y,WANG H,ZHANG L,et al.Two Methods of Selecting Gaussian Kernel Parameters for One-Class SVMand Their Application to Fault Detection[J].KnowledgeBased Systems,2014,59:75-84.
- [12]GAUTAM C,BALAJI R,SUDHARSON K,et al.Localized Multiple Kernel Learning for Anomaly Detection:Oneclass Classification[J].Knowledge-Based Systems,2019,165:241-252.