# CANShield: Deep Learning-Based Intrusion Detection Framework for Controller Area Networks at the Signal-Level

arXiv: https://arxiv.org/abs/2205.01306 · HTML: https://mlsanity.com/paper/2205.01306/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 87 references that are in the map.
- First posted on arXiv 3 May 2022.

## Builds on (most cited first, 13 of 13)

- [GIDS: GAN based Intrusion Detection System for In-Vehicle Network](https://mlsanity.com/paper/1907.07377/) (2019)
- [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)
- [INDRA: Intrusion Detection using Recurrent Autoencoders in Automotive Embedded Systems](https://mlsanity.com/paper/2007.08795/) (2020)
- [CAN-D: A Modular Four-Step Pipeline for Comprehensively Decoding Controller Area Network Data](https://mlsanity.com/paper/2006.05993/) (2020)
- [LATTE: LSTM Self-Attention based Anomaly Detection in Embedded Automotive Platforms](https://mlsanity.com/paper/2107.05561/) (2021)
- [Viden: Attacker Identification on In-Vehicle Networks](https://mlsanity.com/paper/1708.08414/) (2017)
- [Detection of Message Injection Attacks onto the CAN Bus using Similarity of Successive Messages-Sequence Graphs](https://mlsanity.com/paper/2104.03763/) (2021)
- [Time-Based CAN Intrusion Detection Benchmark](https://mlsanity.com/paper/2101.05781/) (2021)
- [TENET: Temporal CNN with Attention for Anomaly Detection in Automotive Cyber-Physical Systems](https://mlsanity.com/paper/2109.04565/) (2021)
- [Detecting CAN Masquerade Attacks with Signal Clustering Similarity](https://mlsanity.com/paper/2201.02665/) (2022)
- [Identifying ECUs Using Inimitable Characteristics of Signals in Controller Area Networks](https://mlsanity.com/paper/1607.00497/) (2016)
- [Long Short-Term Memory Neural Networks for False Information Attack Detection in Software-Defined In-Vehicle Network](https://mlsanity.com/paper/1906.10203/) (2019)

## Built on by (most cited first, 9 of 9)

- [Evaluating lightweight unsupervised online IDS for masquerade attacks in CAN](https://mlsanity.com/paper/2406.13778/) (2024)
- [Adaptive Anomaly Detection for Identifying Attacks in Cyber-Physical Systems: A Systematic Literature Review](https://mlsanity.com/paper/2411.14278/) (2024)
- [Detecting Masquerade Attacks in Controller Area Networks Using Graph Machine Learning](https://mlsanity.com/paper/2408.05427/) (2024)
- [STATGRAPH: Effective In-vehicle Intrusion Detection via Multi-view Statistical Graph Learning](https://mlsanity.com/paper/2311.07056/) (2023)
- [Evaluating False Alarm and Missing Attacks in CAN IDS](https://mlsanity.com/paper/2602.02781/) (2026)
- [DAIRE: A lightweight AI model for real-time detection of Controller Area Network attacks in the Internet of Vehicles](https://mlsanity.com/paper/2604.20771/) (2026)
- [MIDS: Detecting Stealthy Masquerade and Tampering Attacks on CAN Bus via Bidirectional Mamba](https://mlsanity.com/paper/2606.18599/) (2026)
- [CAN We Trust Your Results? A Cross-Dataset Study of Automotive IDS Evaluation](https://mlsanity.com/paper/2606.30430/) (2026)
- [Temporal transformer CAN encoder with federated lightweight heads for anomaly detection](https://mlsanity.com/paper/2610.10613/) (2026)

## Abstract (arXiv)

Modern vehicles rely on a fleet of electronic control units (ECUs) connected through controller area network (CAN) buses for critical vehicular control. With the expansion of advanced connectivity features in automobiles and the elevated risks of internal system exposure, the CAN bus is increasingly prone to intrusions and injection attacks. As ordinary injection attacks disrupt the typical timing properties of the CAN data stream, rule-based intrusion detection systems (IDS) can easily detect them. However, advanced attackers can inject false data to the signal/semantic level, while looking innocuous by the pattern/frequency of the CAN messages. The rule-based IDS, as well as the anomaly-based IDS, are built merely on the sequence of CAN messages IDs or just the binary payload data and are less effective in detecting such attacks. Therefore, to detect such intelligent attacks, we propose CANShield, a deep learning-based signal-level intrusion detection framework for the CAN bus. CANShield consists of three modules: a data preprocessing module that handles the high-dimensional CAN data stream at the signal level and parses them into time series suitable for a deep learning model; a data analyzer module consisting of multiple deep autoencoder (AE) networks, each analyzing the time-series data from a different temporal scale and granularity, and finally an attack detection module that uses an ensemble method to make the final decision. Evaluation results on two high-fidelity signal-based CAN attack datasets show the high accuracy and responsiveness of CANShield in detecting advanced intrusion attacks.