A research team led by Professor Jeon Sanghoon of Kookmin University, in collaboration with a joint research team from Korea University, won the Best Artifact Award at USENIX VehicleSec 2026, a world-renowned conference on vehicle security
- 26.08.13 / 홍유민
A joint research team comprising the Mobility Cybersecurity Research Lab (MoSE), led by Professor Jeon Sanghoon of the Department of Automotive IT Convergence at Kookmin University’s College of Automotive Mobility (President Jeong Seung Ryul), and the Hacking Response Technology Research Lab (HCRL) led by Professor Kim Huy Kang of Korea University won the Best Artifact Award at “USENIX VehicleSec 2026,” an international symposium on vehicle security. .
VehicleSec is a leading international symposium in the field of vehicle security held in conjunction with the USENIX Security Symposium, the world’s most prestigious security conference. This year’s event took place in Baltimore, USA, from Monday, August 10, to Tuesday, August 11. The joint research team earned the award by proposing “AutoHack,” a cybersecurity dataset collected from vehicles in motion.
The paper accepted for publication, titled “AutoHack: A Physically Verified Multi-Bus CAN Dataset for Intrusion Detection System Evaluation,” lists students Ahn Se-jun (Kookmin University) and Song Yu-chan (Korea University) as co-first authors, with students Kim Hyun-sung (Kookmin University) and Baek Seung-jin (Korea University) as co-authors, and Professors Jeon Sanghoon and Kim Huy Kang from both universities as corresponding authors.
This research has been highly praised for overcoming the limitations of existing automotive security datasets, which failed to reflect real-world driving environments. While the risk of hacking has increased as vehicles have become more advanced and intelligent, existing datasets for artificial intelligence (AI) security technologies designed to detect hacking signals have been heavily reliant on simulations or single “CAN bus” (in-vehicle communication network) environments.
In response, a joint research team led by Professor Jeon Sanghoon of Kookmin University’s Department of Automotive IT Convergence synchronized and collected traffic from three major in-vehicle communication networks at intervals of one-millionth of a second, enabling the analysis of interactions between networks and the propagation paths of hacking attacks. Furthermore, by including irregular communication data, the team established a foundation for precisely validating the limitations of existing intrusion detection models that relied solely on pattern analysis.
The research team’s paper earned all three badges—openness, functionality, and reproducibility—in the academic society’s artifact (research output) evaluation, thereby gaining recognition for the study’s openness and reliability. The team made the developed dataset and benchmark code publicly available on “Zenodo,” a free academic information-sharing platform, so that anyone can utilize them.
Professor Jeon Sanghoon of Kookmin University stated, “This achievement demonstrates that inter-university collaborative research and the operation of hands-on security competitions can lead to world-class research,” adding, “We hope the published dataset will serve as a shared resource for automotive cybersecurity research and talent development both domestically and internationally.”
This research was conducted with support from the Future Automotive Project Team at Kookmin University, the lead institution for the Future Automotive sector under the Innovative Convergence University for Advanced Fields (COSS) project, which is funded by the Ministry of Education and the National Research Foundation of Korea. The Future Automotive Project Team has hosted the AutoHack competition annually, providing a real-vehicle-based attack and defense training environment to college students nationwide. This award is regarded as a prime example of how the hands-on educational infrastructure established by the project team has led to international research achievements.
Meanwhile, Kookmin University, celebrating its 80th anniversary, is preparing for a new leap toward the next 100 years under the vision of “A University Setting the Standard for Higher Education” and the slogan “Make the Rule, Break the Rule.” To this end, the university has established “KMU VISION 2035: EDGE,” its mid- to long-term development strategy, and selected eight specialized fields to intensively strengthen the university’s competitiveness.
Focusing on “Mobility”—one of the eight specialized fields—Kookmin University’s Future Automotive Business Unit is continuously expanding industry-academia collaboration with domestic and international automotive companies to enhance expertise in future automobiles and mobility software. In line with this initiative, Kookmin University plans to cultivate talent equipped with practical skills and convergent thinking to lead the future mobility industry.

|
This content is translated from Korean to English using the AI translation service DeepL and may contain translation errors such as jargon/pronouns. If you find any, please send your feedback to kookminpr@kookmin.ac.kr so we can correct them.
|
|
A research team led by Professor Jeon Sanghoon of Kookmin University, in collaboration with a joint research team from Korea University, won the Best Artifact Award at USENIX VehicleSec 2026, a world-renowned conference on vehicle security |
||||
|---|---|---|---|---|
|
2026-08-13
15
A joint research team comprising the Mobility Cybersecurity Research Lab (MoSE), led by Professor Jeon Sanghoon of the Department of Automotive IT Convergence at Kookmin University’s College of Automotive Mobility (President Jeong Seung Ryul), and the Hacking Response Technology Research Lab (HCRL) led by Professor Kim Huy Kang of Korea University won the Best Artifact Award at “USENIX VehicleSec 2026,” an international symposium on vehicle security. . The research team’s paper earned all three badges—openness, functionality, and reproducibility—in the academic society’s artifact (research output) evaluation, thereby gaining recognition for the study’s openness and reliability. The team made the developed dataset and benchmark code publicly available on “Zenodo,” a free academic information-sharing platform, so that anyone can utilize them.
|
||||






