Adaptive DBSCAN-Enhanced Oversampling for Imbalanced Network Intrusion Detection: A Boundary-Aware Approach
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (5) , 1-18
Abstract
No abstract availableKeywords
Funding Information
- National Key Research and Development Program of China (2023YFB2703802)
- National Natural Science Foundation of China (62272120)
- Scientific Research Fund of Zhejiang Provincial Education Department (Y202559768)
- Chongqing Research Program of Basic Research and Frontier Technology, China (CSTB2025NSCQ-GPX1309)
- Jointly Funded Projects of Universities, Institutes and Enterprises under the Basic Research Program of Guangzhou (2024A03J0325)
This publication has 27 references indexed in Scilit:
- Interpretable intrusion detection for IoT security: A SHAP-enhanced NGBoost modelComputer Networks, 2025
- Improving SMOTE via fusing conditional VAE for data-adaptive noise filteringApplied Intelligence, 2025
- SMOTE oversampling algorithm based on generative adversarial networkCluster Computing, 2025
- An oversampling technique based on noise detection and geometryApplied Soft Computing, 2025
- PPFCM-SMOTE: a novel balancing system for anomaly detection in IoT edge using probabilistic possibilistic fuzzy clustering and SMOTEInternational Journal of Information Technology, 2024
- Towards unbalanced multiclass intrusion detection with hybrid sampling methods and ensemble classificationApplied Soft Computing, 2024
- Extreme minority class detection in imbalanced data for network intrusionComputers & Security, 2022
- Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTEInformation Sciences, 2019
- A detailed analysis of the KDD CUP 99 data set2009
- ADASYN: Adaptive synthetic sampling approach for imbalanced learning2008