Can LLMs Classify CVEs? Investigating LLMs Capabilities in Computing CVSS Vectors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Marchiori, Francesco, Donadel, Denis, Conti, Mauro
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916691043155968
author Marchiori, Francesco
Donadel, Denis
Conti, Mauro
author_facet Marchiori, Francesco
Donadel, Denis
Conti, Mauro
contents Common Vulnerability and Exposure (CVE) records are fundamental to cybersecurity, offering unique identifiers for publicly known software and system vulnerabilities. Each CVE is typically assigned a Common Vulnerability Scoring System (CVSS) score to support risk prioritization and remediation. However, score inconsistencies often arise due to subjective interpretations of certain metrics. As the number of new CVEs continues to grow rapidly, automation is increasingly necessary to ensure timely and consistent scoring. While prior studies have explored automated methods, the application of Large Language Models (LLMs), despite their recent popularity, remains relatively underexplored. In this work, we evaluate the effectiveness of LLMs in generating CVSS scores for newly reported vulnerabilities. We investigate various prompt engineering strategies to enhance their accuracy and compare LLM-generated scores against those from embedding-based models, which use vector representations classified via supervised learning. Our results show that while LLMs demonstrate potential in automating CVSS evaluation, embedding-based methods outperform them in scoring more subjective components, particularly confidentiality, integrity, and availability impacts. These findings underscore the complexity of CVSS scoring and suggest that combining LLMs with embedding-based methods could yield more reliable results across all scoring components.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10713
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can LLMs Classify CVEs? Investigating LLMs Capabilities in Computing CVSS Vectors
Marchiori, Francesco
Donadel, Denis
Conti, Mauro
Cryptography and Security
Common Vulnerability and Exposure (CVE) records are fundamental to cybersecurity, offering unique identifiers for publicly known software and system vulnerabilities. Each CVE is typically assigned a Common Vulnerability Scoring System (CVSS) score to support risk prioritization and remediation. However, score inconsistencies often arise due to subjective interpretations of certain metrics. As the number of new CVEs continues to grow rapidly, automation is increasingly necessary to ensure timely and consistent scoring. While prior studies have explored automated methods, the application of Large Language Models (LLMs), despite their recent popularity, remains relatively underexplored. In this work, we evaluate the effectiveness of LLMs in generating CVSS scores for newly reported vulnerabilities. We investigate various prompt engineering strategies to enhance their accuracy and compare LLM-generated scores against those from embedding-based models, which use vector representations classified via supervised learning. Our results show that while LLMs demonstrate potential in automating CVSS evaluation, embedding-based methods outperform them in scoring more subjective components, particularly confidentiality, integrity, and availability impacts. These findings underscore the complexity of CVSS scoring and suggest that combining LLMs with embedding-based methods could yield more reliable results across all scoring components.
title Can LLMs Classify CVEs? Investigating LLMs Capabilities in Computing CVSS Vectors
topic Cryptography and Security
url https://arxiv.org/abs/2504.10713