The Internet of Things (IoT) compromises multiple devices connected via a network to perform numerous activities. The large amounts of raw user data handled by IoT operations have driven researchers and developers to provide guards against any malicious threats. Blockchain is a technology that can give connected nodes means of security, transparency, and distribution. IoT devices could guarantee data centralization and availability with shared ledger technology. Federated learning (FL) is a new type of decentralized machine learning (DML) where clients collaborate to train a model and share it privately with an aggregator node. The integration of Blockchain and FL enabled researchers to apply numerous techniques to hide the shared training parameters and protect their privacy. This study explores the application of this integration in different IoT environments, collectively referred to as the Internet of X (IoX). In this paper, we present a state-of-the-art review of federated learning and Blockchain and how they have been used in collaboration in the IoT ecosystem. We also review the existing security and privacy challenges that face the integration of federated learning and Blockchain in the distributed IoT environment. Furthermore, we discuss existing solutions for security and privacy by categorizing them based on the nature of the privacy-preservation mechanism. We believe that our paper will serve as a key reference for researchers interested in improving solutions based on mixing Blockchain and federated learning in the IoT environment while preserving privacy.
Recently, blockchain technology has appeared as a powerful decentralized tool for data integrity protection. The use of smart contracts in blockchain helped to provide a secure environment for developing peer-to-peer applications. Blockchain has been used by the research community as a tool for protection against attacks. The blockchain itself can be the objective of many cyberthreats. In the literature, there are few research works aimed to protect the blockchain against cyberthreats adopting, in most cases, statistical schemes based on smart contracts and causing deployment and runtime overheads. Although, the power of machine learning tools there is insufficient use of these techniques to protect blockchain against attacks. For that reason, we aim, in this paper, to propose a new framework called BChainGuard for cyberthreat detection in blockchain. Our framework’s main goal is to distinguish between normal and abnormal behavior of the traffic linked to the blockchain network. In BChainGuard, the execution of the classification technique will be local. Next, we embed only the decision function as a smart contract. The experimental result shows encouraging results with an accuracy of detection of around 95% using SVM and 98.02% using MLP with a low runtime and overhead in terms of consumed gas.
Machine learning-based (ML) systems are becoming the primary means of achieving the highest levels of productivity and effectiveness. Incorporating other advanced technologies, such as the Internet of Things (IoT), or e-Health systems, has made ML the first choice to help automate systems and predict future events. The execution environment of ML is always presenting contrasting types of threats, such as adversarial poisoning of training datasets or model parameters manipulation. Blockchain technology is known as a decentralized network of blocks that symbolizes means of protecting block content integrity and ensuring secure execution of operations.Existing studies partially incorporated Blockchain into the learning process. This paper proposes a more extensive secure way to protect the decision process of the learning model. Using smart contracts, this study executed the model’s decision by the reversal engineering of the learning model’s decision function from the extracted learning parameters. We deploy Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) classifiers decision functions on-chain for more comprehensive integration of Blockchain. The effectiveness of this proposed approach is measured by applying a case study of medical records. In a safe environment, SVM prediction scores were found to be higher than MLP. However, MLP had higher time efficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.