{
  "id": 57,
  "url": "https://arxiv.org/abs/2607.09936v1",
  "title": "SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification",
  "summary": "Cybersecurity systems must adapt rapidly to emerging threats. However, labeled data for new threat categories is unavailable when those threats first appear. Generalized zero-shot learning offers a natural solution by enabling recognition of unseen classes through auxiliary semantic knowledge rather than labeled examples. Large language models are particularly promising in this setting because they can convert unstructured CTI reports into semantic prototypes for emerging threats. However, apply",
  "authors": "Ivan Alejandro Montoya Sanchez, Anantaa Kotal, Aritran Piplai",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": "meta",
  "regions": null,
  "published_at": "2026-07-10T19:33:47.000Z",
  "fetched_at": "2026-07-14T14:14:15.665Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/57",
  "original_url": "https://arxiv.org/abs/2607.09936v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}