TY  - JOUR
AU  - Kar, Santosh Kumar
AU  - Subudhi, B. Ujalesh
AU  - Mishra, Brojo Kishore
AU  - Mahapatra, Chittaranjan
PY  - 2025
DA  - 2025/10/13
TI  - A Graph-Aware Attention-Driven Ensemble Model for Robust Anomaly Detection in 6G-Enabled Wireless Sensor Networks
JO  - Next-Generation Computing Systems and Technologies
T2  - Next-Generation Computing Systems and Technologies
JF  - Next-Generation Computing Systems and Technologies
VL  - 1
IS  - 1
SP  - 18
EP  - 32
DO  - 10.62762/NGCST.2025.333764
UR  - https://www.icck.org/article/abs/NGCST.2025.333764
KW  - 6G security
KW  - wireless sensor networks
KW  - intrusion detection system
KW  - deep learning
AB  - The integration of sixth-generation (6G) networks with Wireless Sensor Networks (WSNs) creates unprecedented opportunities for developing secure and scalable smart city infrastructures. However, the proliferation of heterogeneous devices and exponential data growth demand more robust security solutions. While existing hybrid deep learning approaches combining convolutional, recurrent, and attention-based architectures show promise in attack detection, they face limitations including high false-positive rates, inadequate modeling of topological dependencies, and vulnerability to adversarial attacks. This paper presents an enhanced intrusion detection framework that integrates Graph Neural Networks (GNNs) for structural dependency learning, cross-attention mechanisms for feature fusion, and stacked ensemble classification for improved decision reliability. Evaluated on Kitsune, 5G-NIDD, and CICIDS-2018 datasets, the framework demonstrates strong adaptability across heterogeneous traffic scenarios and complex attack vectors. Experimental results show remarkable performance with 99.95\% detection accuracy, consistent F1-scores above 99\%, significantly reduced false alarms, and enhanced adversarial resilience. These findings validate the framework's scalability and practical readiness for securing next-generation 6G-enabled smart city infrastructures.
SN  - 3070-3328
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Kar2025A,
  author = {Santosh Kumar Kar and B. Ujalesh Subudhi and Brojo Kishore Mishra and Chittaranjan Mahapatra},
  title = {A Graph-Aware Attention-Driven Ensemble Model for Robust Anomaly Detection in 6G-Enabled Wireless Sensor Networks},
  journal = {Next-Generation Computing Systems and Technologies},
  year = {2025},
  volume = {1},
  number = {1},
  pages = {18-32},
  doi = {10.62762/NGCST.2025.333764},
  url = {https://www.icck.org/article/abs/NGCST.2025.333764},
  abstract = {The integration of sixth-generation (6G) networks with Wireless Sensor Networks (WSNs) creates unprecedented opportunities for developing secure and scalable smart city infrastructures. However, the proliferation of heterogeneous devices and exponential data growth demand more robust security solutions. While existing hybrid deep learning approaches combining convolutional, recurrent, and attention-based architectures show promise in attack detection, they face limitations including high false-positive rates, inadequate modeling of topological dependencies, and vulnerability to adversarial attacks. This paper presents an enhanced intrusion detection framework that integrates Graph Neural Networks (GNNs) for structural dependency learning, cross-attention mechanisms for feature fusion, and stacked ensemble classification for improved decision reliability. Evaluated on Kitsune, 5G-NIDD, and CICIDS-2018 datasets, the framework demonstrates strong adaptability across heterogeneous traffic scenarios and complex attack vectors. Experimental results show remarkable performance with 99.95\\% detection accuracy, consistent F1-scores above 99\\%, significantly reduced false alarms, and enhanced adversarial resilience. These findings validate the framework's scalability and practical readiness for securing next-generation 6G-enabled smart city infrastructures.},
  keywords = {6G security, wireless sensor networks, intrusion detection system, deep learning},
  issn = {3070-3328},
  publisher = {Institute of Central Computation and Knowledge}
}