Blockchain-based Federated Learning Approaches in Internet of Things
applications
Abstract
The Internet of Things (IoT) is a new well-structured emerging
technology with communication of smart devices using the 5G technology,
infrastructures of roads, vehicles, smart cities, traffic systems and
user applications. The IoT applications facilitate providing prompt
emergency responses, and improved quality of vehicles, and road
services, with cost-effective activities in the intelligent
transportation systems. According to the growth of 5G technology and
complex communications between smart devices and intelligent vehicles,
Federated Learning is applied to support privacy and security factors in
safety-critical transportation systems using innovative prediction
methods in Internet of Vehicle (IoV) environments. Therefore, Federated
Learning (FL) approaches can support safety, privacy and security for
the sensitive personal information of users and critical aspects of
vehicles in intelligent transportation systems and IoV. This
comprehensive review paper delves into the innovative integration of
blockchain technology with federated learning and the dynamic domain of
IoV. It extensively analyzes the primary concepts, methodologies, and
challenges associated with the deployment of FL in IoV. This study
categorically examines three main types of federated learning approaches
vertical, horizontal, and decentralized each tailored to specific IoV
communication scenarios like Vehicle-to-Vehicle (V2V),
Vehicle-to-Infrastructure (V2I), and Vehicle-to-Cloud (V2C). The study
emphasizes various applications of FL, including cyber-attack detection,
data sharing, traffic prediction, and privacy preservation based on
critical Quality of Service (QoS) factors. Finally, some main challenges
and new open issues are discussed and assessed for federated machine
learning approaches in the IoV.