ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models

Authors: Shivansh Chopra, Hussain Ahmad, Diksha Goel, Claudia Szabo
Published: 2024-12-06 | Updated: 2025-05-20

Source: https://arxiv.org/abs/2412.04756

PDF: https://arxiv.org/pdf/2412.04756

AIにより推定されたラベル

計算効率 プロンプトインジェクション テキスト生成手法

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

The increasing frequency and sophistication of cybersecurity vulnerabilities in software systems underscores the need for more robust and effective vulnerability assessment methods. However, existing approaches often rely on highly technical and abstract frameworks, which hinder understanding and increase the likelihood of exploitation, resulting in severe cyberattacks. In this paper, we introduce ChatNVD, a support tool powered by Large Language Models (LLMs) that leverages the National Vulnerability Database (NVD) to generate accessible, context-rich summaries of software vulnerabilities. We develop three variants of ChatNVD, utilizing three prominent LLMs: GPT-4o Mini by OpenAI, LLaMA 3 by Meta, and Gemini 1.5 Pro by Google. To evaluate their performance, we conduct a comparative evaluation focused on their ability to identify, interpret, and explain software vulnerabilities. Our results demonstrate that GPT-4o Mini outperforms the other models, achieving over 92 accuracy and the lowest error rates, making it the most reliable option for real-world vulnerability assessment.