An Intrusion Detection System based on Deep Learning for CAN Bus
Subject Areas : ICTFatemeh Asghariyan 1 , Mohsen Raji 2 *
1 - Shiraz University
2 - Shiraz University
Keywords: In-vehicle network, Controller area network (CAN), Intrusion detection, Convolutional neural network (CNN), Adversarial Training,
Abstract :
In recent years, with the advancement of automotive electronics and the development of modern vehicles with the help of embedded systems and portable equipment, in-vehicle networks such as the controller area network (CAN) have faced new security risks. Since the CAN bus lacks security systems such as authentication and encryption to deal with cyber-attacks, the need for an intrusion detection system to detect attacks on the CAN bus seem to be very necessary. In this paper, a deep adversarial neural network (DACNN) is proposed to detect various types of security intrusions in CAN buses. For this purpose, the DACNN method, which is an extension of the CNN method using adversarial learning, detects intrusion in three stages; In the first stage, CNN acts as a feature descriptor and the main features are extracted, and in the second stage, the discriminating classifier classifies these features and finally, the intrusion is detected using the adversarial learning. In order to show the efficiency of the proposed method, a real open source dataset was used in which the CAN network traffic on a real vehicle during message injection attacks is recorded on a real vehicle. The obtained results show that the proposed method performs better than other machine learning methods in terms of false negative rate and error rate, which is less than 0.1% for DoS and drive gear forgery attack and RPM forgery attack while this rate is less than 0.5% for fuzzy attack.
1] Khan, Zadid, et al. "Long Short-Term Memory Neural Network-Based Attack Detection Model for In-Vehicle Network Security." IEEE Sensors Letters 4.6 (2020): 1-4.
[2] Song, Hyun Min, Jiyoung Woo, and Huy Kang Kim. "In-vehicle network intrusion detection using deep convolutional neural network." Vehicular Communications 21 (2020): 100198.
[3] Islam, Riadul, and Rafi Ud Daula Refat. "Improving CAN bus security by assigning dynamic arbitration IDs." Journal of Transportation Security 13.1 (2020): 19-31.
[4] Linxi Zhang, et al. "A Hybrid Approach Toward Efficient and Accurate Intrusion Detection for In-Vehicle Networks." Digital Object Identifier 10.1109/ACCESS.2022.3145007
[5] Wang, Chundong, et al. "A distributed anomaly detection system for in-vehicle network using HTM." IEEE Access 6 (2018): 9091-9098.
[6] Park, Seunghyun, and Jin-Young Choi. "Hierarchical anomaly detection model for in-vehicle networks using machine learning algorithms." Sensors 20.14 (2020): 3934.
[7] E. Seo, H.M. Song, H.K. Kim, "GIDS: GAN based intrusion detection system for in-vehicle network", 2018 16th Annual Conference on Privacy, Security and Trust (PST), IEEE, 2018, pp. 1–6.
[8] Barletta, Vita Santa, et al. "Intrusion Detection for In-Vehicle Communication Networks: An Unsupervised Kohonen SOM Approach." Future Internet 12.7 (2020): 119.
[9] Barletta, Vita Santa, et al. "A Kohonen SOM Architecture for Intrusion Detection on In-Vehicle Communication Networks." Applied Sciences 10.15 (2020): 5062.
[10] Kosmanos, Dimitrios, et al. "A novel intrusion detection system against spoofing attacks in connected electric vehicles." Array 5 (2020): 100013.
[11] Luo, Shengda, et al. "Complementary Deep and Shallow Learning with Boosting for Public Transportation Safety." Sensors 20.17 (2020): 4671.
[12] Qin, Zhi-Quan, Xing-Kong Ma, and Yong-Jun Wang. "ADSAD: An unsupervised attention-based discrete sequence anomaly detection framework for network security analysis." Computers & Security 99 (2020): 102070.
[13] Alom, Md Zahangir, and Tarek M. Taha. "Network intrusion detection for cyber security using unsupervised deep learning approaches." 2017 IEEE National Aerospace and Electronics Conference (NAECON). IEEE, 2017.
[14] Hwang, Ren-Hung, et al. "An unsupervised deep learning model for early network traffic anomaly detection." IEEE Access 8 (2020): 30387-30399.
[15] Zavrak, Sultan, and Murat İskefiyeli. "Anomaly-based intrusion detection from network flow features using variational autoencoder." IEEE Access 8 (2020): 108346-108358.
[16] Merrill, Nicholas, and Azim Eskandarian. "Modified autoencoder training and scoring for robust unsupervised anomaly detection in deep learning." IEEE Access 8 (2020): 101824-101833.
[17] Huang, Jiabo, et al. "Unsupervised deep learning by neighbourhood discovery." International Conference on Machine Learning. PMLR, 2019.
[18] Aljemely, Anas H., et al. "A novel unsupervised learning method for intelligent fault diagnosis of rolling element bearings based on deep functional auto-encoder." Journal of Mechanical Science and Technology 34.11 (2020): 4367-4381.
[19] Schlegl, Thomas, et al. "f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks." Medical image analysis 54 (2019): 30-44.
[20] CAR-HACKING DATASET, https://ocslab.hksecurity.net/Datasets/CAN-intrusion-dataset
[21] T. Han, C. Liu, W. Yang, D. Jiang, "A novel adversarial learning framework in deep convolutional neural network " intelligent diagnosis of mechanical faults, Knowledge-Based Syst. 165 (2019) 474–487.