전기전자학회논문지 (Journal of IKEEE)

  • 제27권4호
  • /
  • Pages.524-530
  • /
  • 2023
  • /
  • 1226-7244(pISSN)
  • /
  • 2288-243X(eISSN)
한국전기전자학회 (Institute of Korean Electrical and Electronics Engineers)
권호 표지
DOI QR코드

DOI QR Code

초경량 Convolutional Neural Network를 이용한 차량용 Intrusion Detection System의 설계 및 구현

Design and Implementation of Automotive Intrusion Detection System Using Ultra-Lightweight Convolutional Neural Network

  • Myeongjin Lee (School of Electronic Engineering and Department of Intelligent Semiconductor, Soongsil University) ;
  • Hyungchul Im (School of Electronic Engineering and Department of Intelligent Semiconductor, Soongsil University) ;
  • Minseok Choi (School of Electronic Engineering and Department of Intelligent Semiconductor, Soongsil University) ;
  • Minjae Cha (School of Electronic Engineering and Department of Intelligent Semiconductor, Soongsil University) ;
  • Seongsoo Lee (School of Electronic Engineering and Department of Intelligent Semiconductor, Soongsil University)
  • 투고 : 2023.12.14
  • 심사 : 2023.12.22
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 경량화된 CNN(Convolutional Neural Network)을 사용하여 CAN(Controller Area Network) 버스 상의 공격을 탐지하는 효율적인 알고리즘을 제안하고, 이를 기반으로 하는 IDS(Intrusion Detection System)를 FPGA로 설계, 구현 및 검증하였다. 제안한 IDS는 기존의 CNN 기반 IDS에 비해 CAN 버스 상의 공격을 프레임 단위로 탐지할 수 있어서 정확하고 신속한 대응이 가능하다. 또한 제안한 IDS는 기존의 CNN 기반 IDS에 비해 컨볼루션 레이어를 하나만 사용하기 때문에 하드웨어를 크게 줄일 수 있다. 시뮬레이션 및 구현 결과는 제안된 IDS가 CAN 버스 상의 다양한 공격을 효과적으로 탐지한다는 것을 보여준다.

This paper proposes an efficient algorithm to detect CAN (Controller Area Network) bus attack based on a lightweight CNN (Convolutional Neural Network), and an IDS(Intrusion Detection System) was designed, implemented, and verified with FPGA. Compared to conventional CNN-based IDS, the proposed IDS detects CAN bus attack on a frame-by-frame basis, enabling accurate and rapid response. Furthermore, the proposed IDS can significantly reduce hardware since it exploits only one convolutional layer, compared to conventional CNN-based IDS. Simulation and implementation results show that the proposed IDS effectively detects various attacks on the CAN bus.

키워드

과제정보

This work was supported by the R&D Program of the Ministry of Trade, Industry, and Energy (MOTIE) and Korea Evaluation Institute of Industrial Technology (KEIT). (20023805, RS-2022-00155731, RS-2022-00232192)

참고문헌

  1. ISO 11898-1:2015, "Road Vehicles-Controller Area Network (CAN)-Part 1: Data Link Layer and Physical Signaling," https://www.iso.org/standard/63648.html
  2. ISO 9141-3:1998, "Road Vehicles-Diagnostic Systems-Part 3: Verification of the Communication between Vehicle and OBD II Scan Tool," https://www.iso.org/standard/28621.html
  3. K. Koscher, A. Czeskis, F. Roesner, S. Patel, T. Kohno, S. Checkoway, and S. Savage, "Experimental Security Analysis of a Modern Automobile," Proceedings of IEEE Symposium on Security and Privacy, pp.447-462, 2010. DOI: 10.1109/SP.2010.34
  4. S. Woo, H. Jo, and D. Lee, "A Practical Wireless Attack on the Connected Car and Security Protocol for In-Vehicle CAN," IEEE Transactions on Intelligent Transportation systems, vol.16, no.2, pp.993-1006, 2015. DOI: 10.1109/TITS.2014.2351612
  5. C. Lin and A. Sangiovanni-Vincentelli, "Cyber-Security for the Controller Area Network (CAN) Communication Protocol," Proceedings of International Conference on Cyber Security, pp.1-7, 2012. DOI: 10.1109/CyberSecurity.2012.7
  6. S. Khandelwal and S. Shreejith, "A Lightweight FPGA-based IDS-ECU Architecture for Automotive CAN," Proceedings of International Conference on Field Programmable Technology, pp.1-6, 2019.
  7. E. Seo, H. Song, and H. Kim, "GIDS: GAN Based Intrusion Detection System for In-Vehicle Network," Proceedings of Annual Conference on Privacy, Security, and Trust, pp.1-6, 2018. DOI: 10.1109/PST.2018.8514157
  8. H. Im, D. Lee, and S. Lee, "Intrusion Detection System for In-Vehicle Network to Improve Detection Performance Considering Attack Counts and Attack Types," Korean.electr.elctron.eng., vol.26, no.4, pp.622-627, 2022.
  9. H. Son, J. Woo, and H. Kim. "In-Vehicle Network Intrusion Detection Using Deep Convolutional Neural Network," Vehicular Communications, vol.21, pp.100198, 2020. DOI: 10.1016/j.vehcom.2019.100198
  10. "Hacking and Countermeasure Research Lab. Car-Hacking Dataset". https://ocslab.hksecurity.net/Datasets/car-hackingdataset
  11. Y. Wu and C. Huang, "Efficient Dynamic Fixed-Point Quantization of CNN Inference Accelerators for Edge Devices," Proceedings of International Symposium on VLSI Design, Automation and Test, pp.1-4, 2019. DOI: 10.1109/VLSI-DAT.2019.8742040