Abstract

     Security and privacy in the Internet of Things (IoT) other significant challenges, primarily because of the vast scale and deployment of IoT networks. Blockchain-based solutions support decentralized protection and privacy. In this study, a private blockchain-based smart home network architecture for estimating intrusion detection empowered with a Fused Real-Time Sequential Deep Extreme Learning Machine (RTS-DELM) system model is proposed. This study investigates the methodology of RTS-DELM implemented in blockchain-based smart homes to detect any malicious activity. The approach of data fusion and the decision level fusion technique are also implemented to achieve enhanced accuracy. This study examines the numerous key components and features of the smart home network framework more extensively. The Fused RTS-DELM technique achieves a very significant level of stability with a low error rate for any intrusion activity in smart home networks. The simulation findings indicate that this suggested technique successfully optimizes smart home networks for monitoring and detecting harmful or intrusive activities.

Introduction

     A smart home is connected to the Internet, allowing users to manage a variety of smart gadgets, each of which serves an important purpose in the home for the user and their family. The IoT is the foundation of an intelligent home network, connecting disparate intelligent devices such as smartphones, smart computers, and wearable devices. Citizens’ lives can be made easier and safer by making their homes more open and secure. The smart home provides useful resources such as monitoring habits and even safety tests, which have compelled consumers and system developers to conduct extensive research.

     Blockchain-type systems and unified “cloud-like” computing networks can be used to solve these problems. Blockchain was developed in 2008 by Satoshi Nakamoto and includes a time-stamped set of malicious evidence documentation managed by a network of autonomous networks [1]. Blockchain architecture consists of a series of blocks linked together by simple cryptography. The three main concepts underlying the operation of blockchain technologies are inflexibility, decentralization, and transparency. The three roles have been remarkably effective, exposing them to a wide range of digital currency technologies, such as the functionality of mobile vehicles, mobile phones, and embedded systems. While the blockchain platform is secure and anonymous, there are some issues with its current implementation. For example, Sybil attacks by generations of false identities to manipulate the community have become more complex.

Conclusions

     In this study, the idea of a smart contract in blockchain technology is employed to validate the user’s identity for accessibility to centralized smart home services. The most significant benefit of this research is the demonstration of how easy it is to receive facilities and how secure the resources are. There is no need to have redundant authentication because no other third-party users can access smart home systems, even if another user tries to access an already used resource. Intrusion detection in smart homes, especially in the context of assessment and prediction, remains a key concern. In the meantime, recent advances in the blockchain and machine learning sectors have demonstrated tremendous promise to accomplish these aims. Discussing the need for an efficient approach, this study provided a compact and efficient mechanism for intrusion prevention. An RTS-DELM approach was developed, and also data fusion techniques were presented to optimize multi-sensor networks. Numerous measures were used to assess the feasibility of the proposal. The consistency of RTS-DELM findings showed that the proposed method is more successful than others. The suggested RTS-DELM solution obtained an exceptionally high rate of success, showing 95.28% accuracy. The findings obtained are encouraging, and we will continue to investigate more applications for the device through the deployment of more datasets and varying frameworks.