Salvato in:
Dettagli Bibliografici
Autori principali: Bonhomme, Cédric, Dulaunoy, Alexandre
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.03607
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918083496509440
author Bonhomme, Cédric
Dulaunoy, Alexandre
author_facet Bonhomme, Cédric
Dulaunoy, Alexandre
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03607
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification
Bonhomme, Cédric
Dulaunoy, Alexandre
Cryptography and Security
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.
title VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification
topic Cryptography and Security
url https://arxiv.org/abs/2507.03607