Scholarlink

<p>Cybersecurity vulnerabilities represent a critical threat to information systems, often leading to data breaches and operational disruptions. Accurate assessment of vulnerability severity is therefore essential for effective risk prioritization. The Common Vulnerabilities and Exposures (CVE) system maintains a catalog of such vulnerabilities, each accompanied by a brief textual description and a severity score, typically assigned using the Common Vulnerability Scoring System (CVSS). However, manually assigning severity scores is time-consuming and resource-intensive. This challenge highlights the need for automated approaches capable of predicting severity directly from textual data. In this study, we explore the automatic prediction of CVE severity levels from textual descriptions using machine learning. To address class imbalance, we leverage GPT-Neo, a generative language model, to synthetically augment underrepresented categories. We then fine-tune a DeBERTa-based deep learning model for classification, achieving high accuracy in predicting severity levels from text alone. To enhance interpretability, we employ Local Interpretable Model-Agnostic Explanations (LIME) to identify key terms and phrases that most strongly influence model decisions. This approach demonstrates strong predictive performance and provides insight into the linguistic patterns associated with vulnerability severity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated CVE severity prediction using deep learning and explainable AI

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月13日

查看全文
  • Omar Yasin,
  • Qasem Abu Al-Haija,
  • Yousef AbuHour

摘要

Cybersecurity vulnerabilities represent a critical threat to information systems, often leading to data breaches and operational disruptions. Accurate assessment of vulnerability severity is therefore essential for effective risk prioritization. The Common Vulnerabilities and Exposures (CVE) system maintains a catalog of such vulnerabilities, each accompanied by a brief textual description and a severity score, typically assigned using the Common Vulnerability Scoring System (CVSS). However, manually assigning severity scores is time-consuming and resource-intensive. This challenge highlights the need for automated approaches capable of predicting severity directly from textual data. In this study, we explore the automatic prediction of CVE severity levels from textual descriptions using machine learning. To address class imbalance, we leverage GPT-Neo, a generative language model, to synthetically augment underrepresented categories. We then fine-tune a DeBERTa-based deep learning model for classification, achieving high accuracy in predicting severity levels from text alone. To enhance interpretability, we employ Local Interpretable Model-Agnostic Explanations (LIME) to identify key terms and phrases that most strongly influence model decisions. This approach demonstrates strong predictive performance and provides insight into the linguistic patterns associated with vulnerability severity.