OntoLogX uses LLMs to extract actionable threat intelligence from cybersecurity logs

Researchers have developed OntoLogX, an AI agent designed to extract Cyber Threat Intelligence (CTI) from raw cybersecurity logs. The system utilizes Large Language Models (LLMs) combined with a lightweight log ontology and Retrieval Augmented Generation (RAG) to transform unstructured log data into structured Knowledge Graphs (KGs). OntoLogX also predicts MITRE ATT&CK tactics, linking low-level log evidence to higher-level adversarial objectives, and has demonstrated robust KG generation and accurate mapping of adversarial activity on benchmark and real-world datasets. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances CTI extraction from logs, potentially improving threat detection and response capabilities.

RANK_REASON Academic paper detailing a new AI agent for cybersecurity log analysis.

Read on arXiv cs.AI →

• OntoLogX
• Cyber Threat Intelligence
• Large Language Models
• Knowledge Graphs
• Retrieval Augmented Generation
• MITRE ATT&CK
• Luca Cotti
• Hugging Face

• paper
• product
• safety