Structured Extraction of Vulnerabilities in OpenVAS and Tenable WAS Reports Using LLMs

TL;DR

This paper presents an automated method using large language models to extract and structure vulnerabilities from OpenVAS and Tenable WAS reports, transforming unstructured data into standardized formats for improved risk management.

Contribution

It introduces a novel LLM-based approach for extracting vulnerabilities from scanner reports, demonstrating high accuracy and potential for practical risk assessment applications.

Findings

GPT-4.1 and DeepSeek achieved ROUGE-L > 0.7

Method effectively converts complex reports into structured data

Enables vulnerability prioritization and data anonymization

Abstract

This paper proposes an automated LLM-based method to extract and structure vulnerabilities from OpenVAS and Tenable WAS scanner reports, converting unstructured data into a standardized format for risk management. In an evaluation using a report with 34 vulnerabilities, GPT-4.1 and DeepSeek achieved the highest similarity to the baseline (ROUGE-L greater than 0.7). The method demonstrates feasibility in transforming complex reports into usable datasets, enabling effective prioritization and future anonymization of sensitive data.