EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLM-powered threat intelligence: a retrieval-augmented generation approach for cyber attack investigation

Abeer Alhuzali

PeerJ Computer Science · 14.11.2025 · 11 · e3371

DOI: 10.7717/peerj-cs.3371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 14.11.2025. Verfasst von Abeer Alhuzali. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Threat intelligence involves collecting, analyzing, and disseminating information about cyber threats to help organizations proactively defend against attacks. However, manually investigating cyberattacks using Cyber Threat Intelligence (CTI) data is challenging due to its heterogeneity, complexity, and volume. While Large Language Models (LLMs) offer potential for automating attack investigation, they suffer from hallucinations, outdated knowledge, and technical misinterpretations. To address these limitations, we propose a Retrieval-Augmented Generation (RAG)-based LLM system called RAGIntel, which enhances accuracy by retrieving and leveraging structured threat intelligence from MITRE ATT&CK. Our approach employs a hybrid retrieval algorithm with reranking and compression strategies to provide precise, context-aware responses. We evaluated RAGIntel on 339 attack investigation queries drawn from diverse benchmarks, using multiple evaluation metrics, and found that it delivers performance comparable to that of standalone LLMs. This study advances automated attack investigation by leveraging RAG-based LLMs, providing a scalable, accurate, and up-to-date solution for cybersecurity analysts.

Förderung

  • Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah

Zitieren

APA

Alhuzali, A. (2025). LLM-powered threat intelligence: a retrieval-augmented generation approach for cyber attack investigation. PeerJ Computer Science, 11, e3371. https://doi.org/10.7717/peerj-cs.3371

Vancouver

Alhuzali A. LLM-powered threat intelligence: a retrieval-augmented generation approach for cyber attack investigation. PeerJ Computer Science. 2025;11:e3371. doi:10.7717/peerj-cs.3371

BibTeX
@article{Alhuzali2025,
  author = {Alhuzali, Abeer},
  title = {LLM-powered threat intelligence: a retrieval-augmented generation approach for cyber attack investigation},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e3371},
  doi = {10.7717/peerj-cs.3371}
}
Kostenlos starten →