Doo-Seop Choi | Security Researcher

dschoi.png

I am a Ph.D. student researcher at the Software Security Laboratory, Department of Computer Science, Hanyang University, focusing on AI-applied cybersecurity research.

My work mainly explores machine learning and deep learning–based approaches for malicious file detection and network traffic analysis, with an emphasis on data-driven detection pipeline design and empirical evaluation.

Recently, my research has focused on malicious document detection, particularly malicious PDF files, which have become a widely used attack vector. I am especially interested in analyzing how the characteristics of malicious samples evolve over time and incorporating these temporal changes to improve detection performance.

I am broadly interested in how AI technologies can be effectively applied to cybersecurity problems.

Rather than offensive security, my research is oriented toward defensive security, with a specific focus on detection engineering, including feature design and practical deployment-oriented detection models.

news

Jan 15, 2016 A simple inline announcement with Markdown emoji! :sparkles: :smile:
Nov 07, 2015 A long announcement with details
Oct 22, 2015 A simple inline announcement.

selected publications

2025

  1. Elsevier
    Machine learning-based detection method for malicious PDF files: A temporal classification approach
    Doo-Seop Choi, Taeguen Kim, BooJoong Kang, and 1 more author
    Applied Soft Computing, 2025
    DOI
    966 Google Scholar citations
  2. MDPI
    Image-Based Malicious Network Traffic Detection Framework: Data-Centric Approach.
    Doo-Seop Choi, Taeguen Kim, Boojoong Kang, and 1 more author
    Applied Sciences (2076-3417), 2025
    DOI
    0 Google Scholar citations
  3. KIPS
    Windows Malware Family Dataset Construction and Classification
    Kim Tae Young, Doo-Seop Choi, and Eul Gyu Im
    The Transactions of the Korea Information Processing Society, 2025
  4. KIPS
    A Comparative Study of Feature Importance Algorithms and Feature Selection for Static Feature-Based Ransomware Detection
    Jeon Hye Min, Doo-Seop Choi, and Eul Gyu Im
    The Transactions of the Korea Information Processing Society, 2025
  5. KINGPC
    Design of a Cloud-based Integrated Security Software Framework for Android Automotive OS Vehicles
    Doo-Seop Choi and Eul Gyu Im
    The Journal of Korean Institute of Next Generation Computing, 2025