본문 바로가기
  • Home

A Study on Multi-Task CVSS Metric Prediction via Fine-Tuned SLM

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2025, 30(11), pp.63~70
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : September 10, 2025
  • Accepted : October 22, 2025
  • Published : November 28, 2025

Junhyuk Park 1 Jaehee Lee 1 Hyo-Beom Ahn 1

1국립공주대학교

Accredited

ABSTRACT

This study proposes a lightweight model for automatically predicting CVSS v3.1 Base Metrics from vulnerability descriptions. A multi-task architecture using DistilBERT as a shared encoder with parallel classification heads was trained on about 220,000 NVD records. Experiments showed improved efficiency and consistency over single-task approaches, with input token length identified as a key factor affecting performance. The results demonstrate the feasibility of automating CVSS metric prediction, and future work will extend to unstructured data and explainable AI to enhance reliability.

Citation status

* References for papers published after 2024 are currently being built.