AI Summary of Scholarly Research

This page presents an AI-generated summary of a published research paper. The original authors did not write or review this article. [See full disclosure ↓]

OntoLogX turns cybersecurity logs into ontology-grounded knowledge graphs

Research area:computer-science-ai

What the study found

The study found that OntoLogX, an autonomous AI agent, can transform raw cybersecurity logs into ontology-grounded knowledge graphs. The authors also report that it can aggregate these graphs into sessions and predict MITRE ATT&CK tactics, a framework for describing adversary behavior.

Why the authors say this matters

The authors say this matters because system logs contain cyber threat intelligence, but that information is often hard to use due to noise, inconsistent meaning, and fragmentation. The study suggests that reconciling logs into coherent, interoperable knowledge graphs can help extract actionable cyber threat intelligence.

What the researchers tested

The researchers tested OntoLogX, which combines a lightweight log ontology, retrieval augmented generation, and iterative correction steps. They evaluated it on public datasets and real-world honeypot datasets, and they used multiple LLM backends.

What worked and what didn't

The paper reports robust knowledge graph generation across multiple LLM backends. It also reports accurate mapping of adversarial activity to MITRE ATT&CK tactics, and says the method produced ontology-compliant knowledge graphs.

What to keep in mind

The abstract does not provide detailed limitations or failure cases. It also does not give numerical results or specific comparison baselines in the available summary.

Key points

  • OntoLogX transforms raw cybersecurity logs into ontology-grounded knowledge graphs.
  • The system uses a lightweight log ontology, retrieval augmented generation, and iterative correction.
  • It aggregates knowledge graphs into sessions and predicts MITRE ATT&CK tactics.
  • The authors evaluated the system on public and real-world honeypot datasets.
  • The abstract reports robust graph generation across multiple LLM backends.

Disclosure

Research title:
OntoLogX turns cybersecurity logs into ontology-grounded knowledge graphs
Authors:
Luca Cotti, Idílio Drago, Anisa Rula, Devis Bianchini, Federico Cerutti
Institutions:
Cardiff University, Department of Medical Sciences, University of Brescia, University of Brescia, University of Brescia, University of Brescia, University of Southampton, University of Turin
Publication date:
2026-04-23
OpenAlex record:
View
AI provenance: This post was generated by gpt-5.4-mini (OpenAI). The original authors did not write or review this post.