A Quantum-Optimized Fuzzy Min-Max Neural Network for Securing Wireless Sensor Networks

¹ Dr. D. Princy, ² Mrs. G. K. Karthika, ³ Mrs. C. Mercy Praba, ⁴ Dr. S. Devibala

---

Abstract:

Modern cyber-physical systems use Wireless Sensor Networks (WSNs), which are in principle susceptible to a large variety of cyberattacks because they have a decentralized structure and limited resources. In this paper a new intrusion detection system inspired by quantum optimization, based on the Fuzzy Min-Max Neural Network (FMNN) and quantum-inspired optimization to detect threats efficiently and robustly. The FMNN architecture supports dynamic attention multivariate sequence with the ability to model contextual dependencies very finely in network traffic. Quantum Particle Swarm Optimization (QPSO) is implemented to solve the problem of the large dimension search due to model tuning that guarantees a global optimization offering global conversing along with less computation. The empirical testing test on the network simulation indicates that QPSO-FMNN achieves detection accuracy in training time relative to the classical IDS models. The proposed framework has shown a strong robustness to detect known and zero-day attacks as well as being computationally efficient and thus it is ideally fit in an advanced networking system to provide real time security. The work demonstrates itself in the synergy between quantum-inspired optimization and neural network based deep architectures in state-of-the-art in intelligent network security.

Keywords: Security, intrusion, quantum computing, particle swarm, neural network, and accuracy.

How to cite this article: Princy D, Karthika GK, Praba CM, Devibala S. A Quantum-Optimized Fuzzy Min-Max Neural Network for Securing Wireless Sensor Networks. Int J Drug Deliv Technol. 2026;16(10s): 860-869; DOI: 10.25258/ijddt.16.10s.101

Source of support: Nil.

Conflict of interest: None