Research Goals

Researcher at the Privacy-preserving Machine Learning and Cryptography Lab (PMLC Lab), under the supervision of Prof. Eunsang Lee (이은상). My research broadly focuses on privacy-preserving machine learning and cryptography, with applications to sensitive domains such as healthcare and finance. Motivated by the belief that technology should safeguard people’s everyday peace and expand opportunities to learn and dream, I aim to advance secure and practical methods for future AI systems.

저는 기술이 사람들의 일상을 지키고, 모두가 더 큰 꿈을 그릴 수 있도록 돕는 역할을 해야 한다고 믿습니다.
특히 의료나 금융과 같이 민감한 영역에서 프라이버시 보호 머신러닝과 암호학을 결합하여,
보다 안전하고 실용적인 AI 시스템을 만들어가는 것을 제 연구 목표로 삼고 있습니다.

Education

• M.S. in Computer Science, Georgia Institute of Technology, 2024 (Online)
• B.S. in Statistics, Sookmyung Women’s University, 2017

Publications

A standardized glucose-insulin-potassium infusion protocol in surgical patients: Use of real clinical data from a clinical data warehouse

Tae-jung Oh, Ji-hyung Kook, Se Young Jung, Duck-Woo Kim, Sung Hee Choi, Hong Bin Kim, Hak Chul Jang (2021). "A standardized glucose-insulin-potassium infusion protocol in surgical patients: Use of real clinical data from a clinical data warehouse." Diabetes Research and Clinical Practice, 174:108756.

Research Experience

• Jul 2025 - Present: Researcher
  Privacy-Preserving Machine Learning and Cryptography Lab, Seoul, South Korea
  • Participating in weekly lab meetings and literature reviews on homomorphic encryption and federated learning.
  • Building foundational expertise in cryptographic techniques for privacy-preserving machine learning.
  • Preparing to conduct research on combining homomorphic encryption with federated learning to develop secure and practical AI systems.
  • Supervisor: Prof. Eunsang Lee (이은상)
• May 2025 - Jul 2025: Research Project (Intro to Research Course - CS 8803)
  Georgia Institute of Technology, Atlanta, GA, USA
  • Designed and wrote a full research proposal: “A Systematic Review of Practical Challenges in Applying Homomorphic Encryption to Privacy-Preserving Machine Learning.”
  • Conducted a group project using a Systematic Literature Review (SLR) methodology, gaining experience in defining research questions, applying inclusion/exclusion criteria, and synthesizing findings.
  • Participated in a structured peer review process, giving and receiving feedback that improved clarity, feasibility, and academic rigor.
  • Learned collaborative academic writing with LaTeX (Overleaf) and research planning under realistic semester constraints.
• Jan 2018 - Mar 2021: Research Assistant (Data Analyst), Department of Endocrinology
  Seoul National University Bundang Hospital, Gyeonggi-do, South Korea
  • Preprocessed and analyzed clinical datasets (7,000+ patients) for endocrinology research projects.
  • Conducted pilot study using continuous glucose monitoring data to discover predictors of glycemic control.
  • Contributed to a paper in Diabetes Research and Clinical Practice on a standardized GIK infusion protocol.
  • Supervisor: Prof. Tae-jung Oh (오태정)

Work Experience

• Jul 2020 - Sep 2023: Data Analyst, Department of Data Planning
  KB Financial Group, Seoul, South Korea
  • Standardized and organized inconsistent customer data across subsidiaries, enabling unified data access.
  • Trained staff from seven subsidiaries on Customer Journey Maps (CJM) to improve retention in digital services.
  • Provided one-on-one training on dashboard design and automation using Tableau.
• Mar 2018 - Apr 2020: Junior Data Analyst, Department of Data
  Croquis Inc. (Kakao Style / Zigzag), Seoul, South Korea
  • Automated 17 ETL workflows with Python, enhancing data accuracy by 15% and improving reporting reliability.
  • Analyzed purchase and browsing data to optimize product recommendations and marketing strategies.
  • Built custom dashboards in Tableau and R-Shiny to enable data-driven decisions for business teams.
  • Conducted internal training in Python, R, and Tableau to improve organizational data literacy.

Skills

• Programming & Tools: Python, R, SQL, PySpark, C/C++, Git, Docker, LaTeX
• Machine Learning & Data Science: Privacy-Preserving Machine Learning (Federated Learning, Differential Privacy, Homomorphic Encryption), Deep Learning, Statistical Modeling, Data Analysis
• Security & Cryptography: Background from Introduction to Information Security (OMSCS CS6035); building expertise in homomorphic encryption and its applications to federated learning
• Data Visualization: Tableau, R-Shiny, Matplotlib, ggplot2