# Evaluating lightweight unsupervised online IDS for masquerade attacks in CAN

arXiv: https://arxiv.org/abs/2406.13778 · HTML: https://mlsanity.com/paper/2406.13778/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 75 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 14 of 14)

- [PyOD: A Python Toolbox for Scalable Outlier Detection](https://mlsanity.com/paper/1901.01588/) (2019)
- [Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2405.14325/) (2024)
- [CANet: An Unsupervised Intrusion Detection System for High Dimensional CAN Bus Data](https://mlsanity.com/paper/1906.02492/) (2019)
- [A Comprehensive Guide to CAN IDS Data & Introduction of the ROAD Dataset](https://mlsanity.com/paper/2012.14600/) (2020)
- [Element-centric clustering comparison unifies overlaps and hierarchy](https://mlsanity.com/paper/1706.06136/) (2017)
- [CAN-D: A Modular Four-Step Pipeline for Comprehensively Decoding Controller Area Network Data](https://mlsanity.com/paper/2006.05993/) (2020)
- [CANShield: Deep Learning-Based Intrusion Detection Framework for Controller Area Networks at the Signal-Level](https://mlsanity.com/paper/2205.01306/) (2022)
- [Detection of Message Injection Attacks onto the CAN Bus using Similarity of Successive Messages-Sequence Graphs](https://mlsanity.com/paper/2104.03763/) (2021)
- [Detecting In-vehicle Intrusion via Semi-supervised Learning-based Convolutional Adversarial Autoencoders](https://mlsanity.com/paper/2204.01193/) (2022)
- [Time-Based CAN Intrusion Detection Benchmark](https://mlsanity.com/paper/2101.05781/) (2021)
- [can-train-and-test: A Curated CAN Dataset for Automotive Intrusion Detection](https://mlsanity.com/paper/2308.04972/) (2023)
- [Detecting CAN Masquerade Attacks with Signal Clustering Similarity](https://mlsanity.com/paper/2201.02665/) (2022)
- [Performance comparison of timing-based anomaly detectors for Controller Area Network: a reproducible study](https://mlsanity.com/paper/2307.04561/) (2023)
- [Benchmarking Frameworks and Comparative Studies of Controller Area Network (CAN) Intrusion Detection Systems: A Review](https://mlsanity.com/paper/2402.06904/) (2024)

## Built on by (most cited first, 3 of 3)

- [Detecting Masquerade Attacks in Controller Area Networks Using Graph Machine Learning](https://mlsanity.com/paper/2408.05427/) (2024)
- [Temporal cross-validation impacts multivariate time series subsequence anomaly detection evaluation](https://mlsanity.com/paper/2506.12183/) (2025)
- [Evaluating False Alarm and Missing Attacks in CAN IDS](https://mlsanity.com/paper/2602.02781/) (2026)

## Abstract (arXiv)

Vehicular controller area networks (CANs) are susceptible to masquerade attacks by malicious adversaries. In masquerade attacks, adversaries silence a targeted ID and then send malicious frames with forged content at the expected timing of benign frames. As masquerade attacks could seriously harm vehicle functionality and are the stealthiest attacks to detect in CAN, recent work has devoted attention to compare frameworks for detecting masquerade attacks in CAN. However, most existing works report offline evaluations using CAN logs already collected using simulations that do not comply with the domain's real-time constraints. Here we contribute to advance the state of the art by presenting a comparative evaluation of four different non-deep learning (DL)-based unsupervised online intrusion detection systems (IDS) for masquerade attacks in CAN. Our approach differs from existing comparative evaluations in that we analyze the effect of controlling streaming data conditions in a sliding window setting. In doing so, we use realistic masquerade attacks being replayed from the ROAD dataset. We show that although evaluated IDS are not effective at detecting every attack type, the method that relies on detecting changes in the hierarchical structure of clusters of time series produces the best results at the expense of higher computational overhead. We discuss limitations, open challenges, and how the evaluated methods can be used for practical unsupervised online CAN IDS for masquerade attacks.