i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler

2026-07-07

AI Summary

This work addresses the lack of systematicity and interpretability in identifying attack paths and generating security hardening strategies within complex networks. It proposes a novel approach that integrates planning compilation with large language models through an instruction-driven attack connectivity graph. For the first time, this method combines planning compilation—offering completeness and reliability guarantees—with the reasoning capabilities of large language models to enable comprehensive security profiling, precise attack path identification, generation of diverse hardening strategies, and natural language explanations. The framework supports efficient “what-if” analyses, significantly enhancing the interpretability and interactivity of cybersecurity decision-making.

Abstract

i-EXAM is a planning-powered tool that helps system administrators to create security profiles of complex networks and perform what-if analyses to identify network hardening strategies. It leverages planning compilation that provides soundness and completeness guarantees to identify attack paths, evaluate security metrics, generate diverse hardening strategies, and explain these strategies in natural language using Large Language Models.

Problem

• network security
• attack path analysis
• security hardening
• what-if analysis
• explainable AI

Innovation

• planning compilation
• attack path analysis
• network hardening
• explainable AI
• large language models