2021/02/06 by Seong Hoon Jeong, Seonghoon Jeong, Boosun Jeon +7 · 10 citations
Computer Science · Engineering · #Artificial intelligence #Automotive industry #C.2.5 #Computer network #Computer science #Cryptography and Security (cs.CR) #Embedded system #Engineering #Ethernet #FOS: Computer and information sciences #FOS: Electrical engineering #Internet Traffic Analysis and Secure E-voting #Intrusion detection system #Machine Learning (cs.LG) #Network Security and Intrusion Detection #Network packet #Real-time computing #Systems and Control (eess.SY) #Testbed #Vehicular Ad Hoc Networks (VANETs) #cs.CR #cs.LG #cs.SY #eess.SY #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2102.03546
published in arXiv (Cornell University) (Cornell University) · 35 pages, 9 figures, accepted to Vehicular Communications (Elsevier)
arxiv created 2021/02/06 · openalex publication_date 2021/02/06 · arxiv updated 2021/02/09 · openalex created_date 2021/02/15 · openalex updated_date 2026/08/05
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.