SOME/IP 에서의 시퀀셜 모델 기반 침입탐지 시스템
Intrusion Detection System Based on Sequential Model in SOME/IP
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
전방충돌 방지 보조 또는 지능형 주행 제어 기능 등이 현대의 자동차에 탑재됨에 따라 차에서 교환되는 데이터 양이 급증하고 있다. 따라서, 기존의 CAN 통신으로는 전송속도의 한계가 있어 넓은 대역폭과 양방향 통신을 지원하는 오토모티브 이더넷, 특히 SOME/IP가 널리 채택되고 있다. SOME/IP는 다양한 자동차 운영체제와 호환되는 표준 프로토콜로 차내 구성 요소간의 연결성을 높여준다. 하지만 SOME/IP 자체에는 암호화나 인증이 구현되어 있지 않아 악의적인 패킷 주입, 프로토콜 위반과 같은 공격에 취약한 문제가 있다. 본 논문에서는, 이러한 공격들을 효과적으로 탐지하기 위해 SOME/IP에서 딥러닝 기반의 침입탐지 시스템을 제안하였다. 제안된 침입탐지시스템의 성능을 6가지 공격 패턴을 활용하여 테스트 하였고 정확도 94%, 6가지 공격의 평균 F1-score은 0.94로 높은 성능을 달성할 수 있었다.
Abstract
Front Collision-Avoidance Assist (FCA) or Smart Cruise Control (SCC) is installed in a modern vehicle, and the amount of data exchange between ECUs increases rapidly. Therefore, Automotive Ethernet, especially SOME/IP, which supports wide bandwidth and two-way communication, is widely adopted to overcome the bandwidth limitation of traditional CAN communication. SOME/IP is a standard protocol compatible with various automobile operating systems, and improves connectivity between components in the vehicle. However, no encryption or authentication process is defined in the SOME/IP protocol itself. Therefore, there is a need for a security study on the SOME/IP protocol. This paper proposes a deep learning-based intrusion detection system in SOME/IP and performs six attacks to confirm the performance of the intrusion detection system.
참고문헌 (22)
- "Advanced driver assistance technology names"[URL]
- HLDI Bulletin, "Predicted availability and prevalence of safety features on registered vehicles – a 2020 update", 39(2), pp.1~16 (2022)
- "Automotive ethernet and measurement technology, the link between the past and the future", Techworld, 10~ (2021)
- "Future automotive, global value chain trends and overseas expansion strategies"[URL]
- P. Tumas, "Pedestrian detection in severe weather conditions", IEEE Access, 8, pp.62775~62784 (2020)
- H. Kang, "Car hacking and defense competition on in-vehicle network", Third International Work shop on Automotive and Autonomous Vehicle Security, 2021, pp.25~30 (2021)
- K. H. Park, "This Car is Mine! : Automobile Theft Countermeasure Leveraging Driver Identification with Generative Adversarial Networks", ESCAR ASIA 2019, pp.1~6 (2019)
- "Intrusion detection in CAN bus"[URL]
- S. Jeong, "Convolutional neural networ k-based intrusion detection system for AVTP streams in automotive ethernet-based networks", Vehicular Communi cations, 29, pp.1~11 (2021)
- J. Du, "Security analysis and improvement of vehicle ethernet SOME", IP protocol, 2022, pp.22(18), 1~26
- "Hijacking SOME/IP protocol with man in the middle attack"[URL]
- T. Gehrmann, "Intrusio n detection for SOME", IP : challenges and opportunities, 2020 (2020), 583~587
- M. Iorio, "Securing SOME", IP for in-vehicle service protection, 2020, pp.69(11), 13450~13466
- M. Iorio, "Protecting in-vehicle services : security-e nabled SOME", IP middleware, 2020, pp.15(3), 77~85
- M. Rumez, "An overview of automotive service-oriented architectures and imp lications for security countermeasure s", IEEE Access, 8, pp.221852~221870 (2020)
- Y. Li, "Ori : a greybox fuzzer for SOME", IP protocols in automotive ethernet, 2020 (2020), 495~499
- N. Herold, "Anomaly detection for SOME", IP using complex event processin g, IFIP Network Operations and Management Symposium(NOMS), pp.2016 (2016)[DOI]
- N. Alkhatib, "SOME", IP intrusion detection using deep learning-based sequential mo delsin automotive ethernet networks, 2021 (2021), 0954~0962
- "SOME/IP protocol specification"[URL]
- A. H. Mirza, "Computer network intrusion detection using sequential LSTM Neural Networks autoe ncoders", 2018 26th Signal Processing and Communications Applications Conference (SIU), pp.1~4 (2018)
- S. A. Althubiti, "LSTM for anomaly-based network intrusion detection", 2018 28th Intern ational Telecommunication Networks and Applications Conference (ITNAC), pp.1~3 (2018)
- A. R. Javed, "CANintelliI DS : detecting in-vehicle intrusion attacks on a controller area network Using CNN and attention-based GRU", IEEE Transactions on Network Science and Engineering, 8(2), pp.1456~1466 (2021)