# An Adversarial Attack Defending System for Securing In-Vehicle Networks

arXiv: https://arxiv.org/abs/2008.11278 · HTML: https://mlsanity.com/paper/2008.11278/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [ML Attack Models: Adversarial Attacks and Data Poisoning Attacks](https://mlsanity.com/paper/2112.02797/) (2021)
- [Improving Machine Learning Robustness via Adversarial Training](https://mlsanity.com/paper/2309.12593/) (2023)
- [Statistical Detection of Adversarial examples in Blockchain-based Federated Forest In-vehicle Network Intrusion Detection Systems](https://mlsanity.com/paper/2207.04843/) (2022)
- [A Survey of Learning-Based Intrusion Detection Systems for In-Vehicle Network](https://mlsanity.com/paper/2505.11551/) (2025)
- [SDN-Based False Data Detection With Its Mitigation and Machine Learning Robustness for In-Vehicle Networks](https://mlsanity.com/paper/2506.06556/) (2025)
- [Assessing the Resilience of Automotive Intrusion Detection Systems to Adversarial Manipulation](https://mlsanity.com/paper/2506.10620/) (2025)
- [Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustness](https://mlsanity.com/paper/2512.04264/) (2025)
- [SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions](https://mlsanity.com/paper/2605.12792/) (2026)

## Abstract (arXiv)

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.