TY - GEN
T1 - Hybrid AI-Quantum Model with Attention-Guided Variational Circuits for MSSQL Attack Detection in Wireless Networks
AU - Gaurav, Akshat
AU - Arya, Varsha
AU - Nayak, Amiya
AU - Chui, Kwok Tai
AU - Gupta, Brij B.
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - The increasing prevalence of application-layer attacks, such as MSSQL injection, presents serious security challenges for modern wireless networks. Traditional deep learning-based intrusion detection systems often exhibit high model complexity and limited ability to capture complex feature interactions under imbalanced traffic conditions. To address these issues, this paper proposes a hybrid AI-quantum framework with attention-guided variational quantum circuits for MSSQL attack detection. Network traffic features from the CIC-DDoS2019 dataset are embedded and optimized using the Tunicate Swarm Algorithm, followed by convolutional learning to model local dependencies. A variational quantum circuit with learnable rotation and entanglement parameters captures higher-order feature interactions. Experimental results demonstrate an accuracy of 99.99%, with precision, recall, and F1-score all exceeding 99.99%. Ablation analysis further confirms improved parameter efficiency, highlighting the suitability of the proposed approach for secure and sustainable wireless systems.
AB - The increasing prevalence of application-layer attacks, such as MSSQL injection, presents serious security challenges for modern wireless networks. Traditional deep learning-based intrusion detection systems often exhibit high model complexity and limited ability to capture complex feature interactions under imbalanced traffic conditions. To address these issues, this paper proposes a hybrid AI-quantum framework with attention-guided variational quantum circuits for MSSQL attack detection. Network traffic features from the CIC-DDoS2019 dataset are embedded and optimized using the Tunicate Swarm Algorithm, followed by convolutional learning to model local dependencies. A variational quantum circuit with learnable rotation and entanglement parameters captures higher-order feature interactions. Experimental results demonstrate an accuracy of 99.99%, with precision, recall, and F1-score all exceeding 99.99%. Ablation analysis further confirms improved parameter efficiency, highlighting the suitability of the proposed approach for secure and sustainable wireless systems.
KW - Hybrid AI-Quantum Model
KW - Intrusion Detection System
KW - MSSQL Attack Detection
KW - Quantum Attention
KW - Variational Quantum Circuit
UR - https://www.scopus.com/pages/publications/105043416278
U2 - 10.1109/WCNCW67598.2026.11555691
DO - 10.1109/WCNCW67598.2026.11555691
M3 - Conference contribution
AN - SCOPUS:105043416278
T3 - 2026 IEEE Wireless Communications and Networking Conference Workshops, WCNCW 2026
BT - 2026 IEEE Wireless Communications and Networking Conference Workshops, WCNCW 2026
T2 - 2026 IEEE Wireless Communications and Networking Conference Workshops, WCNCW 2026
Y2 - 13 April 2026 through 16 April 2026
ER -