Quantised Neural Network Accelerators for Low-Power IDS in Automotive Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khandelwal, Shashwat, Walsh, Anneliese, Shreejith, Shanker
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911762886950912
author Khandelwal, Shashwat
Walsh, Anneliese
Shreejith, Shanker
author_facet Khandelwal, Shashwat
Walsh, Anneliese
Shreejith, Shanker
contents In this paper, we explore low-power custom quantised Multi-Layer Perceptrons (MLPs) as an Intrusion Detection System (IDS) for automotive controller area network (CAN). We utilise the FINN framework from AMD/Xilinx to quantise, train and generate hardware IP of our MLP to detect denial of service (DoS) and fuzzying attacks on CAN network, using ZCU104 (XCZU7EV) FPGA as our target ECU architecture with integrated IDS capabilities. Our approach achieves significant improvements in latency (0.12 ms per-message processing latency) and inference energy consumption (0.25 mJ per inference) while achieving similar classification performance as state-of-the-art approaches in the literature.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12240
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantised Neural Network Accelerators for Low-Power IDS in Automotive Networks
Khandelwal, Shashwat
Walsh, Anneliese
Shreejith, Shanker
Cryptography and Security
Hardware Architecture
Machine Learning
Systems and Control
In this paper, we explore low-power custom quantised Multi-Layer Perceptrons (MLPs) as an Intrusion Detection System (IDS) for automotive controller area network (CAN). We utilise the FINN framework from AMD/Xilinx to quantise, train and generate hardware IP of our MLP to detect denial of service (DoS) and fuzzying attacks on CAN network, using ZCU104 (XCZU7EV) FPGA as our target ECU architecture with integrated IDS capabilities. Our approach achieves significant improvements in latency (0.12 ms per-message processing latency) and inference energy consumption (0.25 mJ per inference) while achieving similar classification performance as state-of-the-art approaches in the literature.
title Quantised Neural Network Accelerators for Low-Power IDS in Automotive Networks
topic Cryptography and Security
Hardware Architecture
Machine Learning
Systems and Control
url https://arxiv.org/abs/2401.12240