FedLiTeCAN : A Federated Lightweight Transformer for Fast and Robust CAN Bus Intrusion Detection

TL;DR

This paper introduces FedLiTeCAN, a lightweight Transformer-based model designed for fast and robust intrusion detection in CAN bus systems of connected and autonomous vehicles.

Contribution

It presents a novel lightweight Transformer architecture tailored for real-time CAN bus intrusion detection in autonomous vehicles.

Findings

Achieves high detection accuracy with low latency

Demonstrates robustness against various attack types

Reduces computational complexity for embedded deployment

Abstract

This work implements a lightweight Transformer model for IDS in the domain of Connected and Autonomous Vehicles