The ADBPSO-LightGBM internal threat detection framework based on hybrid data balancing

The misuse of privileges by users can lead to significant reputational and financial losses for enterprises. To reduce the risk of information leakage, it is crucial to detect and analyze abnormal behaviours of internal employees. Firstly, based on the characteristics of internal employee behaviour,...

Full description

Saved in:
Bibliographic Details
Main Authors: Jin-Jie Zheng, Xiu Kan, Jian-Zhen Wu, Zhen Zhang, Xiu-Yu Gao
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Systems Science & Control Engineering
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21642583.2025.2498913
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311778900541440
author Jin-Jie Zheng
Xiu Kan
Jian-Zhen Wu
Zhen Zhang
Xiu-Yu Gao
author_facet Jin-Jie Zheng
Xiu Kan
Jian-Zhen Wu
Zhen Zhang
Xiu-Yu Gao
author_sort Jin-Jie Zheng
collection DOAJ
description The misuse of privileges by users can lead to significant reputational and financial losses for enterprises. To reduce the risk of information leakage, it is crucial to detect and analyze abnormal behaviours of internal employees. Firstly, based on the characteristics of internal employee behaviour, a data filter strategy based on user behaviour is proposed. Then, a data balancing strategy based on the concept of hybrid sampling is introduced. Moreover, to further construct the behaviour model, an improved particle swarm optimization algorithm based on adaptive delay and genetic factors is proposed, and it is used to search for the optimal parameters of LightGBM. Experimental results demonstrate that the proposed method is highly effective in detecting internal threats.
format Article
id doaj-art-982c5aa5ad8d4641b50509894dd21f01
institution Kabale University
issn 2164-2583
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Systems Science & Control Engineering
spelling doaj-art-982c5aa5ad8d4641b50509894dd21f012025-08-20T03:53:17ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832025-12-0113110.1080/21642583.2025.2498913The ADBPSO-LightGBM internal threat detection framework based on hybrid data balancingJin-Jie Zheng0Xiu Kan1Jian-Zhen Wu2Zhen Zhang3Xiu-Yu Gao4School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, People’s Republic of ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, People’s Republic of ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, People’s Republic of ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, People’s Republic of ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, People’s Republic of ChinaThe misuse of privileges by users can lead to significant reputational and financial losses for enterprises. To reduce the risk of information leakage, it is crucial to detect and analyze abnormal behaviours of internal employees. Firstly, based on the characteristics of internal employee behaviour, a data filter strategy based on user behaviour is proposed. Then, a data balancing strategy based on the concept of hybrid sampling is introduced. Moreover, to further construct the behaviour model, an improved particle swarm optimization algorithm based on adaptive delay and genetic factors is proposed, and it is used to search for the optimal parameters of LightGBM. Experimental results demonstrate that the proposed method is highly effective in detecting internal threats.https://www.tandfonline.com/doi/10.1080/21642583.2025.2498913Internal threatfeature selectiondata balancinghigh-dimensional clusteringparticle swarm algorithmthreat detection
spellingShingle Jin-Jie Zheng
Xiu Kan
Jian-Zhen Wu
Zhen Zhang
Xiu-Yu Gao
The ADBPSO-LightGBM internal threat detection framework based on hybrid data balancing
Systems Science & Control Engineering
Internal threat
feature selection
data balancing
high-dimensional clustering
particle swarm algorithm
threat detection
title The ADBPSO-LightGBM internal threat detection framework based on hybrid data balancing
title_full The ADBPSO-LightGBM internal threat detection framework based on hybrid data balancing
title_fullStr The ADBPSO-LightGBM internal threat detection framework based on hybrid data balancing
title_full_unstemmed The ADBPSO-LightGBM internal threat detection framework based on hybrid data balancing
title_short The ADBPSO-LightGBM internal threat detection framework based on hybrid data balancing
title_sort adbpso lightgbm internal threat detection framework based on hybrid data balancing
topic Internal threat
feature selection
data balancing
high-dimensional clustering
particle swarm algorithm
threat detection
url https://www.tandfonline.com/doi/10.1080/21642583.2025.2498913
work_keys_str_mv AT jinjiezheng theadbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT xiukan theadbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT jianzhenwu theadbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT zhenzhang theadbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT xiuyugao theadbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT jinjiezheng adbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT xiukan adbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT jianzhenwu adbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT zhenzhang adbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing
AT xiuyugao adbpsolightgbminternalthreatdetectionframeworkbasedonhybriddatabalancing