Jaewon Noh (노재원)

Education & Experiences

• 2025.01~current : Researcher, AI Safety Evaluation section, AI Safety Institute, ETRI, Korea.

• 2022.05~2024.12 : Senior Researcher, AI policy research section, Software Policy & Research Institute, Korea.

• 2020.09~2021.03 : Visiting scholar,  Information and Intelligent Security (IIS) Laboratory, Kennesaw State University

• 2015~2022 : Ph.D., Department of Computer Science & Engineering, Hanyang University, Korea

• 2011~2015 : B.S., Department of Computer Science & Engineering, Hanyang University, Korea

Projects

• Ministry of Science and ICT, LLM Safety and Trustworthiness Evaluation Methodology Development and Evaluation Support Project — 2026~current, Participating Researcher,  AI Safety Institute, ETRI.

• Ministry of Science and ICT, Establishing the Foundation for Generative AI Safety Evaluation — 2025~current, Participating Researcher,  AI Safety Institute, ETRI.

• Ministry of Science and ICT, Construction of LLM Safety and Trustworthiness Evaluation Datasets — 2025, Participating Researcher, AI Safety Institute, ETRI.

• Ministry of Science and ICT, Research on AI Safety and Policy Response Measures — 2024.06~2024.12, Co-Researcher, Software Policy & Research Institute (SPRi).

• Ministry of Science and ICT, Analysis of Global AI Trustworthiness Trends and Detailed AI Trustworthiness Technologies — 2023.01~2023.12, Principal Investigator, Software Policy & Research Institute (SPRi).

• Ministry of Science and ICT, Research on Improvement Measures for the SP Certification Model — 2022.05~2022.12, Co-Researcher, Software Policy & Research Institute (SPRi).

Publications

• Dasol Choi, Eugenia Kim, Jaewon Noh, Sang Seo, Eunmi Kim, Myunggyo Oh, Yunjin Park, Brigitta Jesica Kartono, Josef Pichlmeier, Helena Berndt, Sai Krishna Mendu, Glenn Johannes Tungka, Özlem Gökçe, Suresh Gehlot, Katherine Pratt, Amanda Minnich, and Haon Park, “XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity,” arXiv preprint arXiv:2605.05662, 2026.

• 노재원, 유재흥, 장진철, 조지연, “AI 위험 유형 및 사례 분석,” SPRi Issue Report, 2024.

• 유재흥, 노재원, 조지연, “AI 안전의 개념과 범위,” SPRi Issue Report, 2024.

• 장진철, 노재원, 유재흥, 조지연, “책임있는 AI를 위한 기업의 노력과 시사점,” SPRi Issue Report, 2024. 

• Jaewon Noh, Yongseok Kwon, and Junggab Son, “Blockchain-Based One-Time Authentication for Secure V2X Communication Against Insiders and Authority Compromise Attacks,” IEEE Internet of Things Journal, 2022. 

• Jeehyeong Kim, Joohan Park, Jaewon Noh, and Sunghyun Cho, "Autonomous Power Allocation based on Distributed Deep Learning for Device-toDevice Communication Underlaying Cellular Network," IEEE Access, vol. 8, pp. 107853-107864, Jun, 2020.

• Jaewon Noh, Sangil Jeon and Sunghyun Cho, "Distributed Blockchain-based Message Authentication Scheme for Connected Vehicles," MDPI Electronics, vol. 9, No. 1, pp. 74, 2020.

Patents

1. SATELLITE COMMUNICATIONS METHOD, C. Park, S. Cho, J. Kim, J. Noh, J. Park, T. Kim, Korea Patent No. 1019476490000 (2019)

2. DVB-S2-based GSE packet detection method in continuous satellite stream, C. Park, S. Cho, J. Kim, J. Noh, J. Park, T. Kim, Korea Patent No. 1019476490000 (2019)

3.  Apparatus and Method for Detecting Rogue AP, S. Cho, J. Kim, J. Noh, Korea Patent No. 1018364810000 (2018)