ECU Identification in CAN Networks via Sampling Point–Based Features
- 주제(키워드) CAN (Controller Area Network) , In-vehicle network , Security , ECU identification
- 발행기관 고려대학교 정보보호대학원
- 지도교수 최원석
- 발행년도 2025
- 학위수여년월 2025. 8
- 학위명 석사
- 학과 및 전공 정보보호대학원 정보보호학과
- 원문페이지 42 p
- 실제URI http://www.dcollection.net/handler/korea/000000305684
- UCI I804:11009-000000305684
- DOI 10.23186/korea.000000305684.11009.0003255
- 본문언어 영어
초록/요약
CAN(Controller Area Network is widely used as a communication protocol among ECUs(Electronic Control Units) in modern vehicles. However, since CAN protocol was not designed with security considerations, it lacks security mechanisms for sender authentication and identification. This structural vulnerability allows attackers to inject unauthorized messages into the CAN network, potentially endangering vehicle safety. Existing methods typically identify the transmitting ECU based on unique electrical or timing characteristics, but are ineffective for ECUs that only receive messages without transmitting. To overcome this limitation, this paper proposes a novel SP(Sampling Point)-based feature for ECU identification, exploiting unique timing characteristics observed during the reception of CAN frames. The proposed approach injects precisely timed bit-flip signals at the bit-level, collects offset-dependent error responses resulting from ECU-specific SP differences, and extracts statistical features to train a machine-learning classifier. Experimental results demonstrate distinct SP-based feature patterns among identically configured Arduino and Raspberry Pi boards, achieving over 90% identification accuracy with a Random Forest classifier.
more목차
ABSTRACT ........................................................................................................................... i
국문 초록 .............................................................................................................................. ii
TABLE OF CONTENTS ..................................................................................................... iv
LIST OF TABLES ............................................................................................................... vi
LIST OF FIGURES ............................................................................................................. vii
CHAPTER 1. Introduction ............................................................................................... - 1 -
CHAPTER 2. Related work ............................................................................................. - 3 -
2.1 Voltage-based ECU Approaches for ECU Identification ................................. - 3 -
2.2 Clock-based Approaches for ECU Identification ............................................. - 3 -
2.3 Comparison with Prior Work ............................................................................ - 4 -
CHAPTER 3. Background ............................................................................................... - 5 -
3.1 CAN Protocol ................................................................................................... - 5 -
3.2 CAN Bit Time and Sample Point ..................................................................... - 6 -
3.3 Synchronization Mechanism............................................................................. - 8 -
3.4 Error Handling .................................................................................................. - 8 -
CHAPTER 4. System Model .......................................................................................... - 10 -
CHAPTER 5. ECU Identification method Based on Sampling Point Features .............. - 12 -
5.1 SP-Based Error Injection and Response Collection ........................................ - 12 -
5.1.1 Injection Design ................................................................................. - 12 -
5.1.2 Ensuring Injection Stability ............................................................... - 13 -
5.2 SP-Based Feature Extraction from ECU Responses ....................................... - 14 -
5.3 Feature-Based Learning and Identification ..................................................... - 15 -
CHAPTER 6. Evaluation ................................................................................................ - 18 -
6.1 Evaluation Setup ............................................................................................. - 18 -
6.1.1 Transmitter ......................................................................................... - 18 -
6.1.2 Receiver ............................................................................................. - 19 -
6.1.3 Training Environment and Evaluation Metrics .................................. - 19 -
6.1.4 Experimental Configuration ............................................................... - 20 -
6.2 Comparison of Error Rate Characteristics Across Heterogeneous Hardware - 21 -
6.3 Error Rate Characteristics Across Uniform Hardware ................................... - 22 -
6.4 Evaluation of Machine Learning–Based ECU Identification ......................... - 23 -
6.4.1 Classification Performance Across Heterogeneous Hardware ........... - 24 -
6.4.2 Classification Performance Across Uniform Hardware ..................... - 25 -
6.5 Error Accumulation and Timing Overhead Analysis ..................................... - 28 -
CHAPTER 7. Conclusion ............................................................................................... - 30 -
REFERENCES ............................................................................................................... - 31 -
