{"ID":2898415,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.03607","arxiv_id":"2507.03607","title":"VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification","abstract":"This paper presents VLAI, a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling faster and more consistent triage ahead of manual CVSS scoring. The model and dataset are open-source and integrated into the Vulnerability-Lookup service.","short_abstract":"This paper presents VLAI, a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling faster and more consistent...","url_abs":"https://arxiv.org/abs/2507.03607","url_pdf":"https://arxiv.org/pdf/2507.03607v1","authors":"[\"Cédric Bonhomme\",\"Alexandre Dulaunoy\"]","published":"2025-07-04T14:28:14Z","proceeding":"cs.CR","tasks":"[\"cs.CR\"]","methods":"[\"Transformer\"]","has_code":false}