Quantum-resilient secure key distribution and deep adaptive intelligence for hybrid IIoT-SDN network defense
Senthil, G. A. and Suganthi, S. U. and Deepa, R. and Deepa, R (2026) Quantum-resilient secure key distribution and deep adaptive intelligence for hybrid IIoT-SDN network defense. The European Physical Journal Plus, 141 (8): 1. pp. 1-21. ISSN 2190-5444
4
Download (2MB)
Abstract
The integration of Industrial Internet of Things (IIoT) with Software-Defined Networking (SDN) enables centralized
control, scalability, and flexible network management. However, IIoT-SDN environments remain vulnerable to intrusion attacks, unauthorized access, high-energy consumption, and latency under dynamic network conditions. Existing security mechanisms often struggle with real-time threat detection, adaptive trust enforcement, and efficient key management. To address these issues, this research proposes a High-dimensional Variational Zero-Trust Hopfield Network (HVZTHN) integrated into the SDN control
plane for secure and efficient IIoT communication. The proposed model uses associative memory and zero-trust principles for
authentication, access control, and intrusion detection. The Bermuda Triangle optimizer is applied to fine-tune the model parameters,
improving detection accuracy and convergence speed. In addition, a lightweight secure key distribution mechanism is introduced to
support reliable encryption and confidential data transmission. The proposed HVZTHN model achieved a network lifetime of 480 rounds, energy consumption of 430 J, latency of 70 s, encryption time of 15.6 s, decryption time of 8.4 s, throughput of 950 Mbps,
CPU usage of 30%, and response time of approximately 950 ms. These results demonstrate that the proposed framework provides
an efficient, scalable, and secure solution for IIoT-SDN networks under high-load conditions.
| Item Type: | Article |
|---|---|
| Subjects: | Computer Science Engineering > Artificial Intelligence |
| Domains: | Computer Science Engineering |
| Depositing User: | Mr IR Admin |
| Date Deposited: | 25 Aug 2026 14:20 |
| Last Modified: | 25 Aug 2026 14:20 |
| URI: | https://ir.vistas.ac.in/id/eprint/22111 |
Dimensions
Dimensions