ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Convolutional Neural Network-based Intrusion Detection System for AVTP Streams in Automotive Ethernet-based Networks
Cited 0 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
정성훈, 전부선, 정보흥, 김휘강
발행일
202106
출처
Vehicular Communications, v.29, pp.1-11
ISSN
2214-2096
출판사
Elsevier
DOI
https://dx.doi.org/10.1016/j.vehcom.2021.100338
협약과제
20HR1100, 오토모티브 이더넷 기반 차량 보안위협 예측․탐지․대응 및 보안성 자동진단 기술개발, 정보흥
초록
Connected and autonomous vehicles (CAVs) are an innovative form of traditional vehicles. Automotive Ethernet replaces the controller area network and FlexRay to support the large throughput required by high-definition applications. As CAVs have numerous functions, they exhibit a large attack surface and an increased vulnerability to attacks. However, no previous studies have focused on intrusion detection in automotive Ethernet-based networks. In this paper, we present an intrusion detection method for detecting audio-video transport protocol (AVTP) stream injection attacks in automotive Ethernet-based networks. To the best of our knowledge, this is the first such method developed for automotive Ethernet. The proposed intrusion detection model is based on feature generation and a convolutional neural network (CNN). To evaluate our intrusion detection system, we built a physical BroadR-Reach-based testbed and captured real AVTP packets. The experimental results show that the model exhibits outstanding performance: the F1-score and recall are greater than 0.9704 and 0.9949, respectively. In terms of the inference time per input and the generation intervals of AVTP traffic, our CNN model can readily be employed for real-time detection.
키워드
Automotive Ethernet, Convolutional neural network, In-vehicle network, Intrusion detection system, Network security, Replay attack
KSP 제안 키워드
Attack Surface, Audio and video, BroadR-Reach, CNN model, Connected autonomous vehicles, Controller area network(CAN), Convolution neural network(CNN), Detection Method, Ethernet-based, F1-score, Feature generation