TY  - EJOU
AU  - Zhu, Gan 
AU  - Yu, Yongtao 
AU  - Deng, Xiaofan 
AU  - Dai, Yuanchen 
AU  - Li, Zhenyuan 

TI  - A Hybrid Split-Attention and Transformer Architecture for High-Performance Network Intrusion Detection
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2025
VL  - 145
IS  - 3
SN  - 1526-1506

AB  - Existing deep learning Network Intrusion Detection Systems (NIDS) struggle to simultaneously capture fine-grained, multi-scale features and long-range temporal dependencies. To address this gap, this paper introduces TransNeSt, a hybrid architecture integrating a ResNeSt block (using split-attention for multi-scale feature representation) with a Transformer encoder (using self-attention for global temporal modeling). This integration of multi-scale and temporal attention was validated on four benchmarks: NSL-KDD, UNSW-NB15, CIC-IDS2017, and CICIOT2023. TransNeSt consistently outperformed its individual components and several state-of-the-art models, demonstrating significant quantitative gains. The model achieved high efficacy across all datasets, with F1-Scores of 99.04% (NSL-KDD), 91.92% (UNSW-NB15), 99.18% (CIC-IDS2017), and 97.85% (CICIOT2023), confirming its robustness.
KW  - Intrusion detection; transformer; resnest; split attention; deep learning

DO  - 10.32604/cmes.2025.074349