Skip to content
Open access

Hierarchical Attack Graph Framework for Infrastructure Defense

Sep 2026 · Symposium on Intelligent Systems and Informatics · pp. 095-100 · 0 citations · 17 references

Abstract

The rapid evolution of cyber threats necessitates a transition from static vulnerability scanning to dynamic, context-aware infrastructure analysis. Current methodologies often fail to translate high-level, executive security concerns into actionable technical queries. This paper presents a novel four-layered (L1–L4) hierarchical framework that supports automated infrastructure security assessment using the STIX 2.1 standard and graph-based reasoning. The main contribution of this work is a four-layer hierarchical translation process that bridges the gap between high-level security inquiries and low-level infrastructure telemetry. An L4-level agentic workflow interprets natural language security questions, enriches them with real-time Cyber Threat Intelligence (CTI), and systematically maps them onto the organization’s network topology, asset configurations, and known vulnerabilities. Our design integrates the Neo4j graph database to ensure data integrity and employs EPSS-driven dynamic weighting for real-time risk calibration. The presented case study illustrates that this vertical integration serves as a general-purpose analytical engine capable of mapping and validating a wide range of cyber-risk scenarios within enterprise IT infrastructures. This significantly reduces the gap between strategic oversight and technical reality.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.