GAT-APG: Graph Attention Network-Based Attack Path Generation for Security Simulation

Existing attack path generation methods face limitations in dynamic simulation environments due to their reliance on static network models and computational inefficiencies when network configurations change frequently. This study proposes GAT-APG, a reinforcement learning framework that combines Gra...

Full description

Saved in:
Bibliographic Details
Main Authors: Min Geun Song, Jaewoong Choi, Huy Kang Kim
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11131165/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223097937297408
author Min Geun Song
Jaewoong Choi
Huy Kang Kim
author_facet Min Geun Song
Jaewoong Choi
Huy Kang Kim
author_sort Min Geun Song
collection DOAJ
description Existing attack path generation methods face limitations in dynamic simulation environments due to their reliance on static network models and computational inefficiencies when network configurations change frequently. This study proposes GAT-APG, a reinforcement learning framework that combines Graph Attention Networks with policy gradient methods to generate adaptive attack paths for security simulation. The approach employs node-centric vulnerability assessment that transforms network traffic data into vulnerability metrics, enabling adaptation to network changes without complete graph recalculation. Experimental validation on controlled graphs and the Kyoto dataset demonstrates competitive performance, achieving 93% accuracy against brute-force methods and showing 69.1% exact matches with Dijkstra’s algorithm on real-world topologies. The framework provides a simulation-ready environment for vulnerability assessment and defensive planning in dynamic networks.
format Article
id doaj-art-8491cf2045184cfc839831ab48c0f00c
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-8491cf2045184cfc839831ab48c0f00c2025-08-25T23:18:44ZengIEEEIEEE Access2169-35362025-01-011314738314739610.1109/ACCESS.2025.360066911131165GAT-APG: Graph Attention Network-Based Attack Path Generation for Security SimulationMin Geun Song0https://orcid.org/0009-0009-1133-9783Jaewoong Choi1https://orcid.org/0009-0007-6828-2760Huy Kang Kim2https://orcid.org/0000-0002-0760-8807Graduate School of Information Security, Korea University, Seoul, Republic of KoreaGraduate School of Information Security, Korea University, Seoul, Republic of KoreaGraduate School of Information Security, Korea University, Seoul, Republic of KoreaExisting attack path generation methods face limitations in dynamic simulation environments due to their reliance on static network models and computational inefficiencies when network configurations change frequently. This study proposes GAT-APG, a reinforcement learning framework that combines Graph Attention Networks with policy gradient methods to generate adaptive attack paths for security simulation. The approach employs node-centric vulnerability assessment that transforms network traffic data into vulnerability metrics, enabling adaptation to network changes without complete graph recalculation. Experimental validation on controlled graphs and the Kyoto dataset demonstrates competitive performance, achieving 93% accuracy against brute-force methods and showing 69.1% exact matches with Dijkstra’s algorithm on real-world topologies. The framework provides a simulation-ready environment for vulnerability assessment and defensive planning in dynamic networks.https://ieeexplore.ieee.org/document/11131165/Cyber attack simulationgraph neural networkreinforcement learning
spellingShingle Min Geun Song
Jaewoong Choi
Huy Kang Kim
GAT-APG: Graph Attention Network-Based Attack Path Generation for Security Simulation
IEEE Access
Cyber attack simulation
graph neural network
reinforcement learning
title GAT-APG: Graph Attention Network-Based Attack Path Generation for Security Simulation
title_full GAT-APG: Graph Attention Network-Based Attack Path Generation for Security Simulation
title_fullStr GAT-APG: Graph Attention Network-Based Attack Path Generation for Security Simulation
title_full_unstemmed GAT-APG: Graph Attention Network-Based Attack Path Generation for Security Simulation
title_short GAT-APG: Graph Attention Network-Based Attack Path Generation for Security Simulation
title_sort gat apg graph attention network based attack path generation for security simulation
topic Cyber attack simulation
graph neural network
reinforcement learning
url https://ieeexplore.ieee.org/document/11131165/
work_keys_str_mv AT mingeunsong gatapggraphattentionnetworkbasedattackpathgenerationforsecuritysimulation
AT jaewoongchoi gatapggraphattentionnetworkbasedattackpathgenerationforsecuritysimulation
AT huykangkim gatapggraphattentionnetworkbasedattackpathgenerationforsecuritysimulation