English

An Adversarial Attack Defending System for Securing In-Vehicle Networks

Machine Learning 2020-09-01 v2 Cryptography and Security

Abstract

In a modern vehicle, there are over seventy Electronics Control Units (ECUs). For an in-vehicle network, ECUs communicate with each other by following a standard communication protocol, such as Controller Area Network (CAN). However, an attacker can easily access the in-vehicle network to compromise ECUs through a WLAN or Bluetooth. Though there are various deep learning (DL) methods suggested for securing in-vehicle networks, recent studies on adversarial examples have shown that attackers can easily fool DL models. In this research, we further explore adversarial examples in an in-vehicle network. We first discover and implement two adversarial attack models that are harmful to a Long Short Term Memory (LSTM)-based detection model used in the in-vehicle network. Then, we propose an Adversarial Attack Defending System (AADS) for securing an in-vehicle network. Specifically, we focus on brake-related ECUs in an in-vehicle network. Our experimental results demonstrate that adversaries can easily attack the LSTM-based detection model with a success rate of over 98%, and the proposed AADS achieves over 99% accuracy for detecting adversarial attacks.

Keywords

Cite

@article{arxiv.2008.11278,
  title  = {An Adversarial Attack Defending System for Securing In-Vehicle Networks},
  author = {Yi Li and Jing Lin and Kaiqi Xiong},
  journal= {arXiv preprint arXiv:2008.11278},
  year   = {2020}
}

Comments

6 pages, 3 figures

R2 v1 2026-06-23T18:06:11.170Z