TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network Security

Network security faces major challenges from sophisticated cyber attacks that exploit lateral movement and evade traditional network intrusion detection mechanisms. To address these challenges, micro-segmentation has proven to be an effective defense strategy for isolating network components and lim...

Full description

Saved in:
Bibliographic Details
Main Authors: Ryozo Masukawa, Sanggeon Yun, Sungheon Jeong, Nathaniel D. Bastian, Mohsen Imani
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11096592/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849390138545668096
author Ryozo Masukawa
Sanggeon Yun
Sungheon Jeong
Nathaniel D. Bastian
Mohsen Imani
author_facet Ryozo Masukawa
Sanggeon Yun
Sungheon Jeong
Nathaniel D. Bastian
Mohsen Imani
author_sort Ryozo Masukawa
collection DOAJ
description Network security faces major challenges from sophisticated cyber attacks that exploit lateral movement and evade traditional network intrusion detection mechanisms. To address these challenges, micro-segmentation has proven to be an effective defense strategy for isolating network components and limiting breach propagation. This paper presents TriageHD, a novel framework that integrates graph-based Hyper-Dimensional Computing (HDC) with a learning-to-rank algorithm to strengthen zero-trust network security. TriageHD constructs dynamic scene graphs from time-based network flow data, integrating feature representations extracted via a self-attention-based payload encoder. It employs a learning-to-rank algorithm with an approximated nDCG loss function, incorporating time-aware relevance and graph-aware HDC to prioritize nodes for segregation, thereby mitigating attack propagation. Experiments on the CIC-IDS-2017 dataset demonstrate that TriageHD outperforms state-of-the-art graph neural networks, including graph convolutional networks, graph attention networks, and graph transformer models, in threat prioritization accuracy. By providing a dynamic micro-segmentation approach, TriageHD significantly enhances automated threat detection and response. This work bridges traditional network security measures with zero-trust paradigms, laying the groundwork for future advancements in dynamic micro-segmentation.
format Article
id doaj-art-06b126d390704ac781ec10c8b8c3d4e7
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-06b126d390704ac781ec10c8b8c3d4e72025-08-20T03:41:46ZengIEEEIEEE Access2169-35362025-01-011313680613681510.1109/ACCESS.2025.359287711096592TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network SecurityRyozo Masukawa0https://orcid.org/0009-0009-8988-1388Sanggeon Yun1https://orcid.org/0000-0002-0488-9666Sungheon Jeong2https://orcid.org/0000-0003-3540-7065Nathaniel D. Bastian3https://orcid.org/0000-0001-9957-2778Mohsen Imani4https://orcid.org/0000-0002-5761-0622Department of Computer Science, University of California at Irvine, Irvine, CA, USADepartment of Computer Science, University of California at Irvine, Irvine, CA, USADepartment of Computer Science, University of California at Irvine, Irvine, CA, USAUnited States Military Academy, West Point, NY, USADepartment of Computer Science, University of California at Irvine, Irvine, CA, USANetwork security faces major challenges from sophisticated cyber attacks that exploit lateral movement and evade traditional network intrusion detection mechanisms. To address these challenges, micro-segmentation has proven to be an effective defense strategy for isolating network components and limiting breach propagation. This paper presents TriageHD, a novel framework that integrates graph-based Hyper-Dimensional Computing (HDC) with a learning-to-rank algorithm to strengthen zero-trust network security. TriageHD constructs dynamic scene graphs from time-based network flow data, integrating feature representations extracted via a self-attention-based payload encoder. It employs a learning-to-rank algorithm with an approximated nDCG loss function, incorporating time-aware relevance and graph-aware HDC to prioritize nodes for segregation, thereby mitigating attack propagation. Experiments on the CIC-IDS-2017 dataset demonstrate that TriageHD outperforms state-of-the-art graph neural networks, including graph convolutional networks, graph attention networks, and graph transformer models, in threat prioritization accuracy. By providing a dynamic micro-segmentation approach, TriageHD significantly enhances automated threat detection and response. This work bridges traditional network security measures with zero-trust paradigms, laying the groundwork for future advancements in dynamic micro-segmentation.https://ieeexplore.ieee.org/document/11096592/Zero-trustnetwork securitydynamic micro-segmentationgraph neural networkhyper-dimensional computinglearning-to-rank algorithm
spellingShingle Ryozo Masukawa
Sanggeon Yun
Sungheon Jeong
Nathaniel D. Bastian
Mohsen Imani
TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network Security
IEEE Access
Zero-trust
network security
dynamic micro-segmentation
graph neural network
hyper-dimensional computing
learning-to-rank algorithm
title TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network Security
title_full TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network Security
title_fullStr TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network Security
title_full_unstemmed TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network Security
title_short TriageHD: A Hyper-Dimensional Learning-to-Rank Framework for Dynamic Micro-Segmentation in Zero-Trust Network Security
title_sort triagehd a hyper dimensional learning to rank framework for dynamic micro segmentation in zero trust network security
topic Zero-trust
network security
dynamic micro-segmentation
graph neural network
hyper-dimensional computing
learning-to-rank algorithm
url https://ieeexplore.ieee.org/document/11096592/
work_keys_str_mv AT ryozomasukawa triagehdahyperdimensionallearningtorankframeworkfordynamicmicrosegmentationinzerotrustnetworksecurity
AT sanggeonyun triagehdahyperdimensionallearningtorankframeworkfordynamicmicrosegmentationinzerotrustnetworksecurity
AT sungheonjeong triagehdahyperdimensionallearningtorankframeworkfordynamicmicrosegmentationinzerotrustnetworksecurity
AT nathanieldbastian triagehdahyperdimensionallearningtorankframeworkfordynamicmicrosegmentationinzerotrustnetworksecurity
AT mohsenimani triagehdahyperdimensionallearningtorankframeworkfordynamicmicrosegmentationinzerotrustnetworksecurity