Real ORNL Automotive Dynamometer (ROAD) CAN Intrusion Dataset

Authors: Miki E. Verma, Miachael D. Iannacone, Robert A. Bridges, Samuel C. Hollifield, Bill Kay, and Frank L. Combs


The Controller Area Network (CAN) protocol is ubiquitous in modern road vehicles, but the protocol lacks many important security properties, such as message authentication. To address these insecurities, a rapidly growing field of research has emerged that seeks to detect tampering, anomalies, or attacks on these networks; this field has developed a wide variety of novel approaches and algorithms to address this problem. One major impediment for the progression of this research area is the lack of high-fidelity peer reviewed datasets with realistic labeled attacks, without which it is difficult to evaluate, compare, and validate these proposed approaches. To help address this, we present the ROAD (Real ORNL Automotive Dynamometer) CAN Intrusion Dataset, adding the first dataset with real advanced attacks to the existing collection of open datasets. This dataset contains anonymized CAN data recorded during ambient driving and during several network attacks. See and capture_metadata.json for additional details


CAN Bus, Controller Area Network, Vehicle Network

Project ID



DOI: 10.13139/ORNLNCCS/1728694


Full Paper


@misc{verma2020road, title={ROAD: The Real ORNL Automotive Dynamometer Controller Area Network Intrusion Detection Dataset (with a comprehensive CAN IDS dataset survey & guide)}, author={Miki E. Verma and Michael D. Iannacone and Robert A. Bridges and Samuel C. Hollifield and Bill Kay and Frank L. Combs}, year={2020}, eprint={2012.14600}, archivePrefix={arXiv}, primaryClass={cs.CR} }

Note: Publication is currently under review for acceptance. Citation will be updated accordingly.