An Intrusion Detection System Based on Machine Learning for CAN-Bus

被引：19

作者：

Tian, Daxin ^{[1
,3
,4
]}

Li, Yuzhou ^{[1
,3
,4
]}

Wang, Yunpeng ^{[1
,3
,4
]}

Duan, Xuting ^{[3
]}

Wang, Congyu ^{[3
]}

Wang, Wenyang ^{[2
]}

Hui, Rong ^{[2
]}

Guo, Peng ^{[2
]}

机构：

[1] Beihang Univ, Beijing Adv Innovat Ctr Big Data & Brain Comp, XueYuan Rd 37, Beijing 100191, Peoples R China

[2] China Automot Technol & Res Ctr, Automot Engn Res Inst, East Xianfeng Rd 68, Tianjin 300300, Peoples R China

[3] Beihang Univ, Sch Transportat Sci & Engn, Beijing Key Lab Cooperat Vehicle Infrastruct Syst, XueYuan Rd 37, Beijing 100191, Peoples R China

[4] Jiangsu Prov Collaborat Innovat Ctr Modern Urban, Si Pai Lou 2, Nanjing 210096, Jiangsu, Peoples R China

来源：

INDUSTRIAL NETWORKS AND INTELLIGENT SYSTEMS, INISCOM 2017 | 2018年 / 221卷

关键词：

CAN-Bus; Information security; IDS; Machine learning; GBDT; Entropy; Detection performance; ATTACK;

D O I：

10.1007/978-3-319-74176-5_25

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The CAN-Bus is currently the most widely used vehicle bus network technology, but it is designed for needs of vehicle control system, having massive data and lacking of information security mechanisms and means. The Intrusion Detection System (IDS) based on machine learning is an efficient active information security defense method and suitable for massive data processing. We use a machine learning algorithm-Gradient Boosting Decision Tree (GBDT) in IDS for CAN-Bus and propose a new feature based on entropy as the feature construction of GBDT algorithm. In detection performance, the IDS based on GBDT has a high True Positive (TP) rate and a low False Positive (FP) rate.

引用

页码：285 / 294

页数：10

共 50 条

[31] Study on Electronic Controlled Diesel Engine Calibration System Based on CAN-bus
Li, Jiehui
Zhang, Luyun
Huang, Tienan
Yu, Qing
MECHANICAL DESIGN AND POWER ENGINEERING, PTS 1 AND 2, 2014, 490-491 : 881 - 885
[32] CAN-bus system provides digital molding control
不详
HYDRAULICS & PNEUMATICS, 2001, 54 (12) : S13 - S13
[33] LSTM-Based Intrusion Detection System for In-Vehicle Can Bus Communications
Hossain, Md Delwar
Inoue, Hiroyuki
Ochiai, Hideya
Fall, Doudou
Kadobayashi, Youki
IEEE ACCESS, 2020, 8 (08) : 185489 - 185502
[34] Securing the CAN bus using deep learning for intrusion detection in vehicles
Ritu Rai
Jyoti Grover
Prinkle Sharma
Ayush Pareek
Scientific Reports, 15 (1)
[35] Design a digital flux transducer based on CAN-BUS
Zhang, XM
Guo, Y
Liu, JM
Zhao, W
ICEMI 2005: Conference Proceedings of the Seventh International Conference on Electronic Measurement & Instruments, Vol 1, 2005, : 640 - 642
[36] Anomaly Intrusion Detection for CAN-FD Bus by Support Vector Machine
Luo F.
Hu Q.
Hou S.
Zhang X.
Hu, Qiang (404huqiang@tongji.edu.cn), 1790, Science Press (48): : 1790 - 1796
[37] Reliability research of vehicle electric window control system based on CAN-bus
Liu, Wansong
Xiao, Wenjun
Hui, Linhu
Wang, Yi
PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ELECTRONIC TECHNOLOGY, 2016, 48 : 255 - 258
[38] 浅析CAN-BUS系统
苗全生
董继明
吴素珍
光盘技术, 2007, (06) : 37 - 38
[39] Process control node based on embedded CAN-bus
Chen, Tao
Xu, Zhe
Chen, Shuangye
Duan, Jianmin
ICIEA 2007: 2ND IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS, VOLS 1-4, PROCEEDINGS, 2007, : 522 - 525
[40] Data Acquisition and Storage Network Based on CAN-Bus
Lu, Lixin
Hua, Jun
Li, Guiqin
Peter, Mitrouchev
ADVANCED MANUFACTURING AND AUTOMATION VII, 2018, 451 : 163 - 168

← 1 2 3 4 5 →