About Me

About Me

SeungHun Lee (이승훈)
AI Engineer, 3billion
Ph.D. (Aug 2026), Network Data Science Lab
Dept. of Computer Software Engineering, Sangmyung University
Email: sh.lee@3billion.io / mr.leesh90@gmail.com

Curriculum Vitae

Professional Experience

  • AI Engineer, 3billion, Seoul, South Korea (2026.3 ~ Present)
    • Developing foundation models for DNA, RNA, and protein sequences.
    • Applying deep learning architectures for large-scale biological sequence modeling.
    • Building scalable training pipelines for large-scale genomic datasets.

Education

  • Ph.D., Dept. of Computer Software Engineering, Sangmyung University (2018.3 ~ 2026.8)
  • M.S., Dept. of Computer Software Engineering, Sangmyung University (2015.3 ~ 2017.2)
  • B.S., Dept. of Computer Software Engineering, Sangmyung University (2009.3 ~ 2015.2)

Current Research Interests

My research focuses on AI-driven modeling of biological sequences, particularly in genomics and molecular biology. I develop foundation models to understand genomic function and predict the impact of genetic variants. I am particularly interested in large-scale sequence modeling and representation learning for DNA/RNA/protein data, along with explainable AI (XAI) techniques to improve model interpretability in high-stakes domains.

Doctoral Research

My doctoral research spanned digital finance, network security, and Explainable AI (XAI). In digital finance, I employ a multimodal approach (i.e., text, video, and audio) and user behavior data to analyze crowdfunding platforms, detecting fraudulent campaigns and identifying success factors. For network traffic, I focus on traffic classification and intrusion detection, analyzing both traffic headers and payloads while developing methods to classify traffic patterns. Across these domains, I leverage advanced AI methodologies including natural language processing, pattern analysis, classical machine learning algorithms, transformers, graph neural networks (GNNs), large language models (LLMs), and Agent AI systems. Throughout my work, I integrate XAI techniques to enhance the reliability, transparency, and interpretability of AI-driven solutions.

Publications

Conferences

Journal

Projects

  • Explainability in Graph Neural Networks for Internet Traffic Classification
    (sponsored by the National Research Foundation, Korea) 2023.06 ~ 2025.02
  • Research on Virtualization-based 5G Networks and Cyber Threats
    (sponsored by National Security Research Institute, Korea) 2023.04~2023.10
  • Deep Learning based Internet Traffic Classification: Myths, Realities, and their Explainabilities
    (sponsored by the National Research Foundation, Korea) 2022.06 ~ 2023.05
  • Research on Building a Virtualization-Based 5G Cyber Training Environment
    (sponsored by National Security Research Institute, Korea) 2022.04 ~ 2022.10
  • Multi-modal data-driven Explainable AI Systems and the Future of Digital Finance
    (sponsored by the National Research Foundataion, Korea) 2019.09 ~ 2022.02
  • Towards Explainable AI in Next-Generation Intrusion Detection Systems
    (sponsored by National Security Research Institute, Korea) 2019.04~2019.10
  • Statistics-based Network Behavior Modeling
    (sponsored by National Security Research Institute, Korea) 2018.05 ~ 2018.10
  • Traffic Measurement in Anonymity Networks
    (sponsored by National Security Research Institute, Korea) 2017.04 ~ 2017.10
  • Characterization and Automatic Labeling of Malicious Traffic in Control System Networks
    (sponsored by National Security Research Institute, Korea) 2017.04 ~ 2017.10
  • Network Traffic Classification for Intrusion Detection
    (sponsored by National Security Research Institute, Korea) 2015.06 ~ 2015.12