Research on Multi-Stage Detection of APT Attacks: Feature Selection Based on LDR-RFECV and Hyperparameter Optimization via LWHO
Big Data and Cognitive Computing · 12.08.2025 · 9 (8) · 206
DOI: 10.3390/bdcc9080206 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 12.08.2025. Verfasst von Lihong Zeng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation Project, Inner Mongolia Major science and technology project, Iner Mongolia Autonomous Region science and technology plan project.
Abstract (Originalsprache)
In the highly interconnected digital ecosystem, cyberspace has become the main battlefield for complex attacks such as Advanced Persistent Threat (APT). The complexity and concealment of APT attacks are increasing, posing unprecedented challenges to network security. Current APT detection methods largely depend on general datasets, making it challenging to capture the stages and complexity of APT attacks. Moreover, existing detection methods often suffer from suboptimal accuracy, high false alarm rates, and a lack of real-time capabilities. In this paper, we introduce LDR-RFECV, a novel feature selection (FS) algorithm that uses LightGBM, Decision Trees (DTs), and Random Forest (RF) as integrated feature evaluators instead of single evaluators in recursive feature elimination algorithms. This approach helps select the optimal feature subset, thereby significantly enhancing detection efficiency. In addition, a novel optimization algorithm called LWHO was proposed, which integrates the Levy flight mechanism with the Wild Horse Optimizer (WHO) to optimize the hyperparameters of the LightGBM model, ultimately enhancing performance in APT attack detection. More importantly, this optimization strategy significantly boosts the detection rate during the lateral movement phase of APT attacks, a pivotal stage where attackers infiltrate key resources. Timely identification is essential for disrupting the attack chain and achieving precise defense. Experimental results demonstrate that the proposed method achieves 97.31% and 98.32% accuracy on two typical APT attack datasets, DAPT2020 and Unraveled, respectively, which is 2.86% and 4.02% higher than the current research methods, respectively.
Förderung
- National Natural Science Foundation Project
- Inner Mongolia Major science and technology project
- Iner Mongolia Autonomous Region science and technology plan project
- Inner Mongolia Autonomous Region
- Inner Mongolia Natural Science Foundation Project
- Inner Mongolia Autonomous Region universities innovative research team project
Zitieren
APA
Zeng, L., Li, H., Fu, X., Han, D., Zhou, S., & He, X. (2025). Research on Multi-Stage Detection of APT Attacks: Feature Selection Based on LDR-RFECV and Hyperparameter Optimization via LWHO. Big Data and Cognitive Computing, 9(8), 206. https://doi.org/10.3390/bdcc9080206
Vancouver
Zeng L, Li H, Fu X, Han D, Zhou S, He X. Research on Multi-Stage Detection of APT Attacks: Feature Selection Based on LDR-RFECV and Hyperparameter Optimization via LWHO. Big Data and Cognitive Computing. 2025;9(8):206. doi:10.3390/bdcc9080206
BibTeX
@article{Zeng2025,
author = {Zeng, Lihong and Li, Honghui and Fu, Xueliang and Han, Daoqi and Zhou, Shuncheng and He, Xin},
title = {Research on Multi-Stage Detection of APT Attacks: Feature Selection Based on LDR-RFECV and Hyperparameter Optimization via LWHO},
journal = {Big Data and Cognitive Computing},
year = {2025},
volume = {9},
number = {8},
pages = {206},
doi = {10.3390/bdcc9080206}
}
EUVIMED