Korea and Kookmin University researchers win vehicle security award

A joint research team from Korea University and Kookmin University has received the Best Artifact Award at USENIX VehicleSec 2026, an international symposium for vehicle cybersecurity held in Baltimore, Maryland.

The team was recognized for developing the AutoHack Dataset, a cybersecurity dataset collected from vehicles during actual road driving. Unlike many existing datasets that rely on simulated environments or single in-vehicle networks, AutoHack synchronizes data from three in-vehicle networks simultaneously. This approach allows for the analysis of interactions between networks and the propagation paths of hacking attacks.

The research, titled “AutoHack: A Physically Verified Multi-Bus CAN Dataset for Intrusion Detection System Evaluation,” earned badges for openness, functionality, and reproducibility. The dataset is designed to assist AI-based security systems in distinguishing between normal vehicle operations and malicious cyberattacks.