Deep Learning-Based Intrusion Detection for Automotive Ethernet: Evaluating & Optimizing Fast Inference Techniques for Deployment on Low-Cost Platform
By: Pedro R. X. Carmo , Igor de Moura , Assis T. de Oliveira Filho and more
Potential Business Impact:
Finds car attacks faster on cheap computers.
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 {\mu}s using a Raspberry Pi 4, with AUCROC values of 0.9890.
Similar Papers
Intrusion Detection System Using Deep Learning for Network Security
Cryptography and Security
Finds bad computer stuff to keep networks safe.
Enhanced Intrusion Detection in IIoT Networks: A Lightweight Approach with Autoencoder-Based Feature Learning
Machine Learning (CS)
Protects factory computers from hackers better.
A Survey of Learning-Based Intrusion Detection Systems for In-Vehicle Network
Cryptography and Security
Keeps self-driving cars safe from hackers.