2025/07/01 by Pedro R. X. do Carmo, Igor de Moura, Carmo, Pedro R. X. +7
Computer Science · Engineering · #Autonomous Vehicle Technology and Safety #Bluetooth and Wireless Communication Technologies #C.2.0 #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #I.2.0 #Machine Learning (cs.LG) #Vehicular Ad Hoc Networks (VANETs)
paper · pdf · doi:10.48550/arxiv.2507.01208
openalex publication_date 2025/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Modern vehicles are increasingly connected, and in this context, automotive Ethernet is one of the technologies that promise to provide the necessary infrastructure for intra-vehicle communication. However, these systems are subject to attacks that can compromise safety, including flow injection attacks. Deep Learning-based Intrusion Detection Systems (IDS) are often designed to combat this problem, but they require expensive hardware to run in real time. In this work, we propose to evaluate and apply fast neural network inference techniques like Distilling and Prunning for deploying IDS models on low-cost platforms in real time. The results show that these techniques can achieve intrusion detection times of up to 727 μs using a Raspberry Pi 4, with AUCROC values of 0.9890.