Intrusion Detection Systems for Automotive Networks: Implementing AI-Powered Solutions to Enhance Cybersecurity in In-Vehicle Communication Protocols
Keywords:
automotive networks, intrusion detection systemsAbstract
Autonomous and networked cars need in-vehicle communication network cybersecurity. Modern cars' ECUs communicate via CAN, FlexRay, and Ethernet, creating complex cyberattack-prone networks. IDS prevents network damage. AI-powered CAN and automobile Ethernet automobile IDS is provided by the project. Traditional IDS cannot defend against vehicle network attacks. More complex, adaptable, and scalable solutions are needed. AI-powered IDS using ML and DL can detect zero-day threats and complicated intrusion attempts that rule-based systems miss.
This research compares Signature-based, Anomaly-based, and Hybrid IDS for automotive networks and finds that Anomaly-based IDS is more required due to its flexibility and effectiveness against unexpected assaults. AI-based vehicular communication protocol anomaly IDS design and operation employing supervised, unsupervised, and reinforcement learning. We examine SVM, Random Forests, CNN, LSTM, and Autoencoders for traffic intrusion detection. For resource-constrained automotive settings, detection accuracy, false positive rates, computing overhead, and real-time processing are evaluated.
References
A. Javaid, Q. Niyaz, W. Sun, and M. Alam, "A deep learning approach for network intrusion detection system," in Proc. 9th EAI Int. Conf. Bio-inspired Inf. Commun. Technol. (BICT), New York, NY, USA, 2016, pp. 21–26.
M. Behrisch, L. Bieker, J. Erdmann, and D. Krajzewicz, "SUMO–simulation of urban mobility: An overview," in Proc. 3rd Int. Conf. Adv. Syst. Simul. (SIMUL), Barcelona, Spain, 2011, pp. 55-60.
S. Khan, A. Gumaei, A. Anwar, and H. Daudpota, "A hybrid intelligent approach for effective intrusion detection in connected vehicles," Future Gener. Comput. Syst., vol. 105, pp. 403–412, 2020.
K. Xiao, D. Freeman, and A. Datta, "Leveraging side channels for automotive intrusion detection: A case study," in Proc. ACM SIGSAC Conf. Comput. Commun. Security (CCS), London, UK, 2018, pp. 1-14.
Y. Duan, X. Li, L. Ding, and Z. Gao, "A machine learning-based multi-layer intrusion detection system for VANETs," IEEE Access, vol. 8, pp. 12131-12143, 2020.
G. Loukas, "Machine Learning and Anomaly Detection for Automotive Cybersecurity," in Cybersecurity for Connected Vehicles: Security, Privacy and Safety, 1st ed., B. Suraj and P. Anwar, Eds. Cham, Switzerland: Springer, 2021, ch. 5, pp. 123-146.
R. Bhatia, S. Malik, and A. Kaul, "Machine learning techniques for cyber attack detection in vehicular ad-hoc networks," Int. J. Commun. Syst., vol. 34, no. 6, p. e4753, 2021.
C. Miller and C. Valasek, "Remote exploitation of an unaltered passenger vehicle," Black Hat USA, Las Vegas, NV, USA, 2015, pp. 1–91.
T. Tong, X. Cheng, X. Yang, J. Wang, and W. Liu, "Automotive intrusion detection using deep neural networks: A survey," IEEE Commun. Surveys Tuts., vol. 23, no. 4, pp. 2115–2143, 2021.
S. Song, S. Yoo, and B. Kang, "A hybrid anomaly detection approach combining deep learning with expert knowledge for industrial control systems," IEEE Trans. Ind. Informat., vol. 16, no. 4, pp. 2651-2661, 2020.
B. Subba, S. Biswas, and S. Karmakar, "A neural network-based system for intrusion detection and attack classification in autonomous vehicles," IEEE Trans. Intell. Transp. Syst., vol. 23, no. 1, pp. 123-133, 2022.
R. Mitchell and I. R. Chen, "A survey of intrusion detection techniques for cyber-physical systems," ACM Comput. Surv., vol. 46, no. 4, pp. 1–29, 2014.
M. Habler and H. Hadeli, "Integrating anomaly detection systems for smart car cybersecurity," in Proc. IEEE 7th Int. Conf. Inf. Syst. Security Privacy (ICISSP), Prague, Czech Republic, 2021, pp. 99–106.
M. T. Rahman, K. J. Bowers, N. Saxena, and N. Memon, "Detecting anomalous CAN bus messages using a neural network-based intrusion detection system," IEEE Trans. Veh. Technol., vol. 71, no. 3, pp. 2567-2578, 2022.
A. W. Doosti, S. Srivastava, and A. Choudhary, "A federated learning-based intrusion detection system for vehicular networks," in Proc. IEEE Int. Conf. Smart Infrastruct. Technol. (ICSIT), 2023, pp. 95-101.
H. Abie and I. Balasingham, "Risk-based adaptive security for smart IoT in eHealth," in Proc. Int. Conf. Wireless Mobile Comput. Netw. Commun. (WiMob), Barcelona, Spain, 2012, pp. 597–604.
E. Yaghini, M. H. Manshaei, and A. Barati, "Intrusion detection system for in-vehicle networks using ensemble learning methods," Veh. Commun., vol. 29, p. 100351, 2021.
Z. Durumeric, M. Bailey, and J. A. Halderman, "An internet-wide view of Internet-wide scanning," in Proc. 23rd USENIX Secur. Symp. (USENIX Security), San Diego, CA, USA, 2014, pp. 65–78.
X. Cao, Z. Hu, and Y. Zhang, "Securing V2X communication systems in connected and automated vehicles: A survey," IEEE Trans. Veh. Technol., vol. 70, no. 9, pp. 8823–8836, 2021.
M. Wolf, A. Weimerskirch, and C. Paar, "Security in automotive bus systems," in Proc. 9th Workshop Cryptogr. Hardware Embedded Syst. (CHES), Vienna, Austria, 2007, pp. 7–22.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
