Quantum readout and gradient deep learning model for secure and sustainable data access in IWSN.
| Autor: | Alzubi OA; Prince Abdullah Bin Ghazi Faculty of Information and Communication Technology, Al-Balqa Applied University, Al-Salt, Jordan. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | PeerJ. Computer science [PeerJ Comput Sci] 2022 Jun 06; Vol. 8, pp. e983. Date of Electronic Publication: 2022 Jun 06 (Print Publication: 2022). |
| DOI: | 10.7717/peerj-cs.983 |
| Abstrakt: | The industrial wireless sensor network (IWSN) is a surface-type of wireless sensor network (WSN) that suffers from high levels of security breaches and energy consumption. In modern complex industrial plants, it is essential to maintain the security, energy efficiency, and green sustainability of the network. In an IWSN, sensors are connected to the Internet in a non-monitored environment. Hence, non-authorized sensors can retrieve information from the IWSN. Therefore, to ensure that data access between sensors remains sustainable and secure, energy-efficient authentication and authorization are required. In this article, a novel Quantum Readout Gradient Secured Deep Learning (QR-GSDL) model is proposed to ensure that only trustworthy sensors can access IWSN data. The major objective of this QR-GSDL model is to create secure, energy-efficient IWSN to attain green sustainability and reduce the industrial impact on the environment. First, using the quantum readout and hash function, a registration method is designed to efficiently perform the registration process. Next, a gradient secured deep learning method is adopted to implement the authentication and authorization process in order to ensure energy-saving and secure data access. Simulations are conducted to evaluate the QR-GSDL model and compare its performance with that of three well-known models: online threshold anomaly detection, machine learning-based anomaly detection, and dynamic CNN. The simulation outcomes show that the proposed model is secure and energy-efficient for use in the IWSN. Moreover, the experimental results prove that the QR-SGDL model outperforms the existing models in terms of energy consumption, authentication rate, authentication time, and false acceptance rate. Competing Interests: The author declares that there are no competing interests. (©2022 Alzubi.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|