{
  "id": 14055,
  "url": "https://arxiv.org/abs/2607.24348v1",
  "title": "DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense",
  "summary": "Advanced Persistent Threats (APTs) are difficult to detect and interpret due to their multi-stage and stealthy nature. While recent autonomous defense systems leverage provenance graphs and learning-based models for detection and mitigation, their outputs remain largely machine-oriented and difficult for analysts to interpret. Large language models (LLMs) offer a promising interface for report generation, but often produce hallucinated or weakly grounded content. In this paper, we propose DeepFa",
  "authors": "Trung V. Phan, Tri Gia Nguyen, Thomas Bauschert",
  "category": "research",
  "topics": "military-security",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-27T12:27:17.000Z",
  "fetched_at": "2026-07-28T05:10:12.325Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14055",
  "original_url": "https://arxiv.org/abs/2607.24348v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}