OntoLogX: Ontology‐Guided Knowledge Graph Extraction From Cybersecurity Logs With Large Language Models
Top Cited Papers
Open Access
- 23 April 2026
- journal article
- Published by Wiley in Advanced Intelligent Systems
Abstract
System logs represent a valuable source of cyber threat intelligence (CTI), capturing attacker behaviors, exploited vulnerabilities, and traces of malicious activity. Yet their utility is often limited by a lack of structure, semantic inconsistency, and fragmentation across devices and sessions. Extracting actionable CTI from logs, therefore, requires approaches that can reconcile noisy, heterogeneous data into coherent and interoperable representations. We introduce OntoLogX, an autonomous AI agent that leverages large language models (LLMs) to transform raw logs into ontology‐grounded knowledge graphs (KGs). OntoLogX integrates a lightweight log ontology with retrieval augmented generation and iterative correction steps, ensuring that generated KGs are syntactically and semantically valid. Beyond event‐level analysis, the system aggregates KGs into sessions and employs a LLM to predict MITRE ATT&CK tactics, linking low‐level log evidence to higher‐level adversarial objectives. We evaluate OntoLogX on both public and real‐world honeypot datasets, demonstrating robust KG generation across multiple LLMs backends and accurate mapping of adversarial activity to MITRE ATT&CK tactics. Results highlight the effectiveness of the methodology in constructing ontology‐compliant KGs, along with their value in extracting actionable CTI.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- AttacKG+: Boosting attack graph construction with Large Language ModelsComputers & Security, 2024
- Are LLMs good at structured outputs? A benchmark for evaluating structured output capabilities in LLMsInformation Processing & Management, 2024
- LogPrécis: Unleashing language models for automated malicious log analysisComputers & Security, 2024
- A survey on cybersecurity knowledge graph constructionComputers & Security, 2023
- KRYSTAL: Knowledge graph-based framework for tactical attack discovery in audit dataComputers & Security, 2022
- A comprehensive review study of cyber-attacks and cyber security; Emerging trends and recent developmentsEnergy Reports, 2021
- The SLOGERT Framework for Automated Log Knowledge Graph Construction2021
- A survey on technical threat intelligence in the age of sophisticated cyber attacksComputers & Security, 2018
- Knowledge processes and ontologiesIEEE Intelligent Systems, 2001
- Modelling social action for AI agentsArtificial Intelligence, 1998