Convolutional neural network-based intrusion detection system for AVTP streams in automotive Ethernet-based networks

Connected and autonomous vehicles (CAVs) are an innovative form of traditional vehicles. Automotive Ethernet replaces the controller area network FlexRay to support large throughput required by high-definition applications. As CAVs have numerous functions, they exhibit a attack surface increased vulnerability attacks. However, no previous studies focused on intrusion detection in automotive Ethernet-based networks. In this paper, we present method for detecting audio-video transport protocol (AVTP) stream injection attacks To best our knowledge, is first such developed Ethernet. The proposed model based feature generation convolutional neural (CNN). evaluate system, built physical BroadR-Reach-based testbed captured real AVTP packets. experimental results show that exhibits outstanding performance: F1-score recall greater than 0.9704 0.9949, respectively. terms inference time per input intervals traffic, CNN can readily be employed real-time detection.