Article: DNN and BiGRU-based hierarchical attention network for intrusion detection Journal: International Journal of Business Intelligence and Data Mining (IJBIDM) 2026 Vol.28 No.10 pp.1 - 24 Abstract: To tackle the rising sophistication of cyberattacks and the critical need to enhance intrusion detection capabilities, this study presents a hybrid architecture combining a DNN with an attention mechanism and a BiGRU with an attention mechanism, BiGRU with attention, and an MLP classifier. The model integrates dual DNN-Attention and BiGRU-Attention submodules to capture high-dimensional static features and temporal dependencies, followed by feature fusion and classification via MLP. Evaluated on NSL-KDD and UNSW-NB15 datasets, the model achieves validation accuracies of 99.48% and 98.43%, respectively, with stable convergence and low loss. Comparative results demonstrate superior performance in accuracy, robustness, and generalisation, confirming its effectiveness for practical cybersecurity applications. Inderscience Publishers - linking academia, business and industry through research

Title: DNN and BiGRU-based hierarchical attention network for intrusion detection

Authors: Hui Yan; Hupeng Liu; Ping Yu; Xiaoqing Xu; Mingxin Li; Yunxin Long; Hanlin Chen; Qi Wang; Duo Long

Addresses: Information Engineering College, Suqian University, Suqian, 223800, China ' Jilin Province S&T Innovation Centre for Physical Simulation and Security of Water Resources and Electric Power Engineering, Changchun Institute of Technology, Changchun, 130012, China ' Jilin Province S&T Innovation Centre for Physical Simulation and Security of Water Resources and Electric Power Engineering, Changchun Institute of Technology, Changchun, 130012, China ' Jilin Province S&T Innovation Centre for Physical Simulation and Security of Water Resources and Electric Power Engineering, Changchun Institute of Technology, Changchun, 130012, China ' Information Engineering College, Suqian University, Suqian, 223800, China ' Changchun University of Chinese Medicine, Changchun, 130117, China ' Jilin Province S&T Innovation Centre for Physical Simulation and Security of Water Resources and Electric Power Engineering, Changchun Institute of Technology, Changchun, 130012, China ' Information Engineering College, Suqian University, Suqian, 223800, China ' Information Engineering College, Suqian University, Suqian, 223800, China

Abstract: To tackle the rising sophistication of cyberattacks and the critical need to enhance intrusion detection capabilities, this study presents a hybrid architecture combining a DNN with an attention mechanism and a BiGRU with an attention mechanism, BiGRU with attention, and an MLP classifier. The model integrates dual DNN-Attention and BiGRU-Attention submodules to capture high-dimensional static features and temporal dependencies, followed by feature fusion and classification via MLP. Evaluated on NSL-KDD and UNSW-NB15 datasets, the model achieves validation accuracies of 99.48% and 98.43%, respectively, with stable convergence and low loss. Comparative results demonstrate superior performance in accuracy, robustness, and generalisation, confirming its effectiveness for practical cybersecurity applications.

Keywords: intrusion detection; deep learning; bidirectional gated recurrent unit; attention mechanism; network security.

DOI: 10.1504/IJBIDM.2026.156175

International Journal of Business Intelligence and Data Mining, 2026 Vol.28 No.10, pp.1 - 24

Received: 11 Mar 2026
Accepted: 28 Apr 2026
Published online: 07 Sep 2026 *

Title: DNN and BiGRU-based hierarchical attention network for intrusion detection

Keep up-to-date