Metraipolis › archive › dc_239ac3848941

CoSA: Context-Aware Severity Assessment via Context Analysis with Large Language Models — arXiv:2608.13928

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13928
License (as archived)
CC0-1.0
Archived
2026-10-19T02:29:31.934Z
SHA-256 of the archived text
22c8afeaebfc5f14f096525ce0530919454f3c9aa5e8f0a659a3d259439966b1
Stable URL of this page
https://metraipolis.com/documento/dc_239ac3848941

How to cite

CoSA: Context-Aware Severity Assessment via Context Analysis with Large Language Models — arXiv:2608.13928 — arXiv (en), https://arxiv.org/abs/2608.13928 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_239ac3848941 (Metraipolis archive dc_239ac3848941, sha256 22c8afeaebfc5f14f096525ce0530919454f3c9aa5e8f0a659a3d259439966b1)
BibTeX
@misc{dc239ac3848941,
  title = {CoSA: Context-Aware Severity Assessment via Context Analysis with Large Language Models — arXiv:2608.13928},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13928},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_239ac3848941; sha256 22c8afeaebfc5f14f096525ce0530919454f3c9aa5e8f0a659a3d259439966b1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13928. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate vulnerability severity assessment is essential for prioritizing remediation, yet manually assessing Common Vulnerability Scoring System (CVSS) base metrics remains labor-intensive. Existing automated approaches often fail to capture the repository-level evidence required for assessing many CVSS base metrics. Such repository-aware assessment is challenging because relevant evidence is scattered across the entire repository under heavy noise. To address these challenges, we present CoSA, a Context-aware vulnerability Severity Assessment approach that infers CVSS base metrics from repository artifacts. CoSA constructs a code property graph (CPG) and applies a two-stage repository-pruning strategy: lightweight static pruning to preserve structurally proximal context, followed by an agentic large language model (LLM)-guided pruning step to retain CVSS-relevant context while collecting supporting evidence. The LLM then consolidates the retrieved repository context into compact, CVSS metric-wise textual summaries, which are fed into a lightweight transformer predictor. We also construct a higher-quality repository-level dataset comprising 6,816 CVSS labeled instances spanning 90 Common Weakness Enumeration (CWE) types. Experiments on real-world vulnerabilities show that CoSA consistently outperforms function-level and pure-LLM baselines. It improves prediction accuracy by 14.4% and Macro-F1 by 15.3% over the best-performing baseline, suggesting that explicit, metric-oriented repository context retrieval is crucial for practical and reliable automated severity assessment.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.13928 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:25:38.613Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).