Quantised Neural Network Accelerators for Low-Power IDS in Automotive Networks
This addresses the need for efficient intrusion detection systems in automotive networks, though it is incremental as it applies existing quantization methods to a specific domain.
The paper tackles intrusion detection in automotive CAN networks by developing a low-power quantised neural network accelerator using the FINN framework, achieving 0.12 ms latency and 0.25 mJ per inference while matching state-of-the-art classification performance.
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.