InfoSeverity comes from the source advisory when it gives one. Otherwise the classifier assigns it from the source text.ResearchPeer-reviewedLLM-specificA reliability enhancement framework for LLM-based attack graph generation in software supply chain securitySourceElsevier Security Journals(opens in a new tab)PublishedNovember 14, 2026Record updatedNovember 14, 2026View JSONCopy API URLCopy IEEE citationShare on XShare on LinkedInCopy linkTopicsModel and package supply chain