Quantum readout and gradient deep learning model for secure and sustainable data access in IWSN

Abstract

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.

JACLNet:Application of adaptive code length network in JavaScript malicious code detection

“…Since Accuracy cannot reflect the effect of malicious code detection in malicious code detection, this paper uses Recall , FPR and Precision to supplement. Recall represents the proportion of the malicious samples in the predicted results in the real malicious samples, FPR represents the ratio of the number of false positive examples to the number of all actual negative examples and Precision represents the proportion of the correctly predicted malicious samples in the predicted results [ 36 ]. Its representation is as follows: Where, TP represents the number of samples that detect malicious code as malicious code, FN represents the number of samples that detect malicious code as benign code, and FP represents the number of samples that detect benign code as malicious code.…”

Deception detection with machine learning: A systematic review and statistical analysis

“…Machine Learning has been successfully applied to a large number of fields and functions, such as document classification, computer vision, natural language processing, protein structure prediction, fraud and malware detection [ 8 ], medical diagnosis and data privacy [ 9 ], network and data transmission security [ 10 ], intrusion detection [ 11 ], generative molecular design [ 12 ], and recommendation systems, among others [ 13 ]. Also, it offers a vast set of techniques, providing several opportunities to approach various problems.…”

Optimized Machine Learning-Based Intrusion Detection System for Fog and Edge Computing Environment

“…In contrast, signature-based detection compares incoming traffic to pre-established rules to determine whether to allow or reject it. In the past few years, there have been a variety of study articles developed in the area of intrusion detection systems for fog and edge computing environments [13,14]. Early research concentrated on supervised machine learning and unsupervised machine learning.…”