基于BEGAN的汽车CAN网络入侵检测数据增强方法研究

doi:10.19562/j.chinasae.qcgc.2024.08.006

Abstract

Abstract:

For the data imbalance problem of the current automotive CAN network intrusion detection algorithm due to the lack of attack samples， a CAN intrusion detection data enhancement method based on BEGAN is proposed， which introduces in one-hot coding to image the CAN message features and combines with the constructed Generative Adversarial Network to generate valid samples with the same format as the real attack and with different content. The practicality of the generated enhanced dataset is verified from the perspectives of feature maps， t-SNE visualization， statistical analysis and classifier validation by collecting real vehicle data as real samples for training， which can improve the intrusion detection classifier accuracy. With higher accuracy compared with the traditional oversampling algorithms including Random Oversampling （ROS）， Synthetic Minority Oversampling Technique （SMOTE）， SMOTE combined with Edited Nearest Neighbors （SMOTE-ENN） and Adaptive Synthetic Oversampling （ADASYN）.

Key words: local area network for automotive controller, intrusion detection, generative adversarial networks, data enhancement

Xiang Wang,Pengbo Liu,Jian Zhao,Kefeng Fan,Linhui Li. Research on Data Enhancement Methods of BEGAN-Based Intrusion Detection in Automotive CAN Networks[J].Automotive Engineering, 2024, 46(8): 1394-1402.

Figures/Tables 14

References 32

1	JO H J， CHOI W. A survey of attacks on controller area networks and corresponding countermeasures［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（7）： 6123-6141.
2	RATHORE R S， HEWAGE C， KAIWARTYA O， et al. In-vehicle communication cyber security： challenges and solutions［J］. Sensors， 2022， 22（17）： 6679.
3	KAROPOULOS G， KAMBOURAKIS G， CHATZOGLOU E， et al. Demystifying in-vehicle intrusion detection systems： a survey of surveys and a meta-taxonomy［J］. Electronics， 2022， 11（7）： 1072.
4	REN K， WANG Q， WANG C. et al， The security of autonomous driving： threats， defenses， and future directions［J］. Proceedings of the IEEE， 2020， 108（2）： 357-372.
5	ALDHYANI T H H， ALKAHTANI H. Attacks to automatous vehicles： a deep learning algorithm for cybersecurity［J］. Sensors， 2022， 22（1）： 360.
6	ALALWANY E， MAHGOUB I. Classification of normal and malicious traffic based on an ensemble of machine learning for a vehicle CAN-network［J］. Sensors， 2022， 22（23）： 9195.
7	刘蓬勃，彭海德，赵剑，等. 汽车 CAN 网络的入侵检测模型及装置研究［J］. 实验技术与管理， 2022， 39（3）： 126-131.
	LIU P B， PENG H D， ZHAO J， et al. Research on intrusion detection model and device of automobile controller area network （CAN）［J］. Experimental Technology and Management， 2022， 39（3）： 126-131.
8	YUAN L H， LI X X. WSG-InV： weighted state graph model for intrusion detection on in-vehicle network［C］. 2021 IEEE Wireless Communications and Networking Conference （WCNC）. IEEE， 2021.
9	MARTINELLI F， MERCALDO F， NARDONE V， et al. Car hacking identification through fuzzy logic algorithms［C］. 2017 IEEE International Conference on Fuzzy Systems （FUZZ）. IEEE， 2017， 7.
10	TIAN D X， LI Y Z， WANG Y P， et al. An intrusion detection system based on machine learning for CAN-bus［C］. 2017 Industrial Networks and Intelligent Systems（INISCOM）. Social-Informatics and Telecommunications Engineering， 2017， 221： 285-294.
11	ALSAADE F W， AL-ADHAILEH M H. Cyber attack detection for self-driving vehicle networks using deep autoencoder algorithms［J］. Sensors， 2023， 23（8）： 4086.
12	PARK S， CHOI J Y. Hierarchical anomaly detection model for in-vehicle networks using machine learning algorithms［J］. Sensors， 2020， 20（14）： 3934.
13	ALIWA E， RANA O， PERERA C， et al. Cyberattacks and countermeasures for in-vehicle networks［J］. ACM Computing Surveys， 2021， 54（1）： 21.
14	YUAN L X， YU S Y， YU S Y， et al. A data balancing approach based on generative adversarial network［J］. Future Generation Computer Systems-the International Journal of Escience， 2023， 141： 768-776.
15	ANDRESINI G， APPICE A， DE ROSE L， et al. GAN augmentation to deal with imbalance in imaging-based intrusion detection［J］. Future Generation Computer Systems-the International Journal of Escience， 2021， 123： 108-127.
16	EBRAHIMY H， MIRBAGHERI B， MATKAN A A， et al. Effectiveness of the integration of data balancing techniques and tree-based ensemble machine learning algorithms for spatially-explicit land cover accuracy prediction［J］. Remote Sensing Applications： Society and Environment， 2022： 100785.
17	ZHANG H P， HUANG L L， WU C Q， et al. An effective convolutional neural network based on smote and gaussian mixture model for intrusion detection in imbalanced dataset［J］. Computer Networks， 2020， 177： 107315.
18	周志豪，陈磊，伍翔，等.基于SMOTE-SDSAE-SVM的车载CAN总线入侵检测算法［J］.计算机科学，2022，49（S1）：562-570，801.
	ZHOU Z H， CHEN L， WU X， et al. SMOTE-SDSAE-SVM based vehicle CAN bus intrusion detection algorithm［J］. Computer Science，2022，49（S1）：562-570，801.
19	孙扬威，戚湧.基于聚类混合采样与PSO-Stacking的车载CAN入侵检测方法［J］.计算机工程，2023，49（1）：138-145.
	SUN Y W， QI Y. Intrusion detection method for in-vehicle CAN based on cluster mixed sampling and PSO-Stacking［J］. Computer Engineering， 2023， 49（1）：138-145.
20	MANJU B R， NAIR A R. Classification of cardiac arrhythmia of 12 lead ECG using combination of SMOTEENN， XGBoost and machine learning algorithms［C］. 2019 IEEE International Symposium on Embedded Computing and System Design （ISED）. IEEE， 2019： 48-54.
21	BAE S Y， LEE J， JEONG J， et al. Effective data-balancing methods for class-imbalanced genotoxicity datasets using machine learning algorithms and molecular fingerprints［J］. Computational Toxicology， 2021， 20： 100178.
22	DENG C Y， DENG Z H， LU S， et al. Fault diagnosis method for imbalanced data based on multi-signal fusion and improved deep convolution generative adversarial network［J］. Sensors， 2023， 23（5）： 2542.
23	LEE H， KANG S， CHUNG K S. Robust data augmentation generative adversarial network for object detection［J］. Sensors， 2023， 23（1）： 157.
24	SAMPATH V， MAURTUA I， MARTIN J J A， et al. Intraclass image augmentation for defect detection using generative adversarial neural networks［J］. Sensors， 2023， 23（4）： 1861.
25	KHATRI N， SHRESTHA R， NAM S Y. Security issues with in-vehicle networks， and enhanced countermeasures based on blockchain［J］. Electronics， 2021， 10（8）： 893.
26	GOODFELLOW I J， POUGET-ABADIE J， MIRZA M， et al. Generative adversarial nets［C］. 2014 Advances in Neural Information Processing Systems 27（NIPS）， 2014， 27： 2672-2680.
27	BERTHELOT D， SCHUMM T， METZ L. BEGAN： boundary equilibrium generative adversarial networks［J］. arXiv， 2017.
28	SAMPATH V， MAURTUA I， MARTIN J J A， et al. Intraclass image augmentation for defect detection using generative adversarial neural networks［J］. Sensors， 2023， 23（4）： 1861.
29	KUMAR V， SINHA D. Synthetic attack data generation model applying generative adversarial network for intrusion detection［J］. Computers & Security， 2023， 125： 103054.
30	CHAWLA N V， BOWYER K W， HALL L O， et al. SMOTE： synthetic minority over-sampling technique［J］. Journal of Artificial Intelligence Research， 2002，16： 321-357.
31	IDAKWO G， THANGAPANDIAN S， LUTTRELL J， et al. Structure-activity relationship-based chemical classification of highly imbalanced Tox21 datasets［J］. Journal of Cheminformatics. 2020， 12（1）： 66.
32	HE H B， BAI Y， GARCIA E A， et al. ADASYN： adaptive synthetic sampling approach for imbalanced learning［C］. 2008 IEEE International Joint Conference on Neural Networks （IJCNN）. IEEE， 2008： 1322-1328.

字节1	字节2	字节3	字节4	字节5	字节6	字节7	字节8
D5	64	FB	00	64	19	FE	0C
D5	64	EC	00	64	19	DA	0A
D5	64	17	01	64	19	3D	09
D5	64	3B	01	64	19	FD	09
D5	64	0E	01	64	19	72	03
D5	64	BF	01	64	19	39	0B

特征	真实CAN报文				生成CAN报文
特征	最大值	最小值	平均值	均方差	最大值	最小值	平均值	均方差
字节1	213	213	213	0	213	213	213	0
字节2	100	100	100	0	100	100	100	0
字节3	255	0	149.38	7 496.85	255	14	143.48	3 543.93
字节4	1	0	0.29	0.21	1	0	0.23	0.45
字节5	100	100	100	0	100	100	100	0
字节6	25	25	25	0	25	25	25	0
字节7	250	0	123.34	5 317.49	245	1	125.62	5 781.88
字节8	16	8	10.75	5.17	15	0	9.80	9.36

ID	报文格式	ID	报文格式
064	D5 64 X₁X₂ 0X₃ 64 19 X₄X₅ X₆X₇	2D5	33 DB X₁X₂ 0X₃ 00 0X₅ X₆X₇ 00
0BA	05 F7 X₁X₂ X₃X₄ 00 00 00 00 00	3B3	03 X₁X₂ X₃X₄ 00 00 00 00 00
2C1	08 FF X₁X₂ X₃X₄ X₅X₆ X₇X₈ 00 X₉X₁₀	4C3	04 0X₁ 12 05 X₂X₃ X₄X₅ 00 X₆X₇
2C4	03 X₁X₂ 00 X₃X₄ 00 80 13 X₅X₆	620	10 64 X₁X₂ 0X₃ 30 60 X₄X₅ 50
2D0	06 X₁X₂ 09 00 10 00 F3 X₃X₄	624	1A 00 43 X₁X₂ X₃X₄ 49 40 X₅X₆

项目	Acc
项目	SVM	RF	KNN	GBDT
原始数据集	71%	70%	68%	74%
增强数据集	88%	94%	99%	95%

算法	Acc
算法	SVM	RF	KNN	GBDT
ROS	72%	72%	69%	74%
SMOTE	73%	73%	70%	76%
SMOTE-ENN	73%	73%	70%	76%
ADASYN	72%	73%	69%	75%
BEGAN	88%	94%	99%	95%

Research on Data Enhancement Methods of BEGAN-Based Intrusion Detection in Automotive CAN Networks

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 32

Related Articles 2

Metrics

Comments

Recommended 0

字节1	字节2	字节3	字节4	字节5	字节6	字节7	字节8
D5	64	FB	00	64	19	FE	0C
D5	64	EC	00	64	19	DA	0A
D5	64	17	01	64	19	3D	09
D5	64	3B	01	64	19	FD	09
D5	64	0E	01	64	19	72	03
D5	64	BF	01	64	19	39	0B

[1]	Yingxiang Cui, Youtong Zhang, Hongqian Wei. An Intrusion Detection System for In-vehicle CAN Network Based on Sample Entropy [J]. Automotive Engineering, 2023, 45(7): 1184-1191.
[2]	Yuxin Guan,Haojie Ji,Zhe Cui,He Li,Liwen Chen. An Overview of Intrusion Detection Methods for In-Vehicle CAN Network of Intelligent Networked Vehicles [J]. Automotive Engineering, 2023, 45(6): 922-935.

字节1	字节2	字节3	字节4	字节5	字节6	字节7	字节8
D5	64	FB	00	64	19	FE	0C
D5	64	EC	00	64	19	DA	0A
D5	64	17	01	64	19	3D	09
D5	64	3B	01	64	19	FD	09
D5	64	0E	01	64	19	72	03
D5	64	BF	01	64	19	39	0B

字节1	字节2	字节3	字节4	字节5	字节6	字节7	字节8
D5	64	FB	00	64	19	FE	0C
D5	64	EC	00	64	19	DA	0A
D5	64	17	01	64	19	3D	09
D5	64	3B	01	64	19	FD	09
D5	64	0E	01	64	19	72	03
D5	64	BF	01	64	19	39	0B