Predicting known Vulnerabilities from Attack News: A Transformer-Based Approach

TL;DR

This paper presents a transformer-based semantic similarity approach to predict CVEs from cybersecurity news, achieving high precision and relevance in identifying vulnerabilities exploited during cyberattacks.

Contribution

It introduces a novel method using MPNet sentence transformer to link attack news descriptions with known vulnerabilities, validated through multiple accuracy assessments.

Findings

81% precision with threshold filtering

70% manual relevance rate

57% reports with exact CVE match

Abstract

Identifying the vulnerabilities exploited during cyberattacks is essential for enabling timely responses and effective mitigation in software security. This paper directly examines the process of predicting software vulnerabilities, specifically Common Vulnerabilities and Exposures (CVEs), from unstructured descriptions of attacks reported in cybersecurity news articles. We propose a semantic similarity-based approach utilizing the multi-qa-mpnet-base-dot-v1 (MPNet) sentence transformer model to generate a ranked list of the most likely CVEs corresponding to each news report. To assess the accuracy of the predicted vulnerabilities, we implement four complementary validation methods: filtering predictions based on similarity thresholds, conducting manual validation, performing semantic comparisons with the first vulnerability explicitly mentioned in each report, and comparing against all CVEs referenced within the report. Experimental results, drawn from a dataset of 100 SecurityWeek news articles, demonstrate that the model attains a precision of 81 percent when employing threshold-based filtering. Manual evaluations report that 70 percent of the predictions are relevant, while comparisons with the initially mentioned CVEs reveal agreement rates of 80 percent with the first listed vulnerability and 78 percent across all referenced CVEs. In 57 percent of the news reports analyzed, at least one predicted vulnerability precisely matched a CVE-ID mentioned in the article. These findings underscore the model's potential to facilitate automated vulnerability identification from real-world cyberattack news reports.