Decentralized Privacy Using Blockchain-Enabled Federated Learning in Fog Computing

Qu, Youyang; Gao, Longxiang; Luan, Tom H.; Xiang, Yong; Yu, Shui; Bai, Li; Zheng, Gavin

doi:10.1109/jiot.2020.2977383

Cited by 340 publications

(143 citation statements)

References 32 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…An adaptation of the FedAvg algorithm for distributed consensus paradigms is proposed. Qu et al [68] use a blockchain-based approach to achieve decentralized privacy protection for FL. A similar block-chain based approach is also discussed in [69] for enabling on-device FL without any central servers.…”

Section: B Technologies For Enabling Fl In Wireless Iotmentioning

confidence: 99%

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Yoshinaga

et al. 2020

IEEE Open J. Comput. Soc.

264

106

View full text Add to dashboard Cite

show abstract

Section: B Technologies For Enabling Fl In Wireless Iotmentioning

confidence: 99%

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Yoshinaga

et al. 2020

IEEE Open J. Comput. Soc.

264

106

View full text Add to dashboard Cite

show abstract

“…In the same context, Lu et al [32] suggested the blockchain empowered asynchronous federated learning-based solution for secure data sharing in Internet of vehicles. Qu et al [39] introduced a new federated learning strategy allowed by blockchain, enabling local learning updates of terminal devices to exchange with a global learning model based on blockchain. It also allowed autonomous machine learning to sustain the global model without centralized authority.…”

Section: Blockchain Learningmentioning

confidence: 99%

SS-ITS: secure scalable intelligent transportation systems

et al. 2021

View full text Add to dashboard Cite

This paper introduces a secure and scalable intelligent transportation and human behavior system to accurately discover knowledge from urban traffic data. The data are secured using blockchain learning technology, where the scalability is ensured by a threaded GPU. In addition, different optimizations are provided to efficiently process data on the GPU. A reinforcement deep learning algorithm is also established to merge local knowledge discovered on each site into global knowledge. To demonstrate the applicability of the proposed framework, intensive experiments have been carried out on well-known intelligent transportation and human behavior data. Our results show that our proposed framework outperforms the baseline solutions for the outlier detection use case.

show abstract

“…Some of the popular training approaches in this direction that may be useful for fog nodes can be transfer learning and knowledge distillation [54], [55]. In addition, to ensure the privacy protection and single point of failure at the fog networks, federated learning emerges as one of the promising solutions for the fog based IIoT networks [56].…”

Section: B Requirements For Fog Networkmentioning

confidence: 99%

BlockEdge: Blockchain-Edge Framework for Industrial IoT Networks

et al. 2020

View full text Add to dashboard Cite

Industry 4.0 encompasses a promise of a new industrial revolution in terms of providing secure, intelligent, autonomous and self-adaptive industrial IoT (IIoT) networks. Key industrial applications and systems will be significantly more complex due to the involvement of the vast number of different devices and diverse nature of various stakeholders and service providers. These complex industrial processes, services and applications also have strict requirements in terms of performance-latency in particular-and resource-efficiency, together with high standards for security and trust. In this context, Blockchain and Edge Computing emerge as prominent technologies to address the mentioned essential requirements and to further strengthen the rise of the new era of digitization. The Edge computing paradigm ensures low latency services for IIoT applications while optimizing the network usage, whereas Blockchain provides a decentralized way for ensuring data integrity, trust and security. In this paper, we propose a 'BlockEdge' framework that combines these two enabling technologies to address some of the critical issues faced by the current IIoT networks. We verify the feasibility of our approach by evaluating the performance and resource-efficiency of BlockEdge in terms of latency, power consumption and network usage, through simulations against non-Blockchain solution.

show abstract

Decentralized Privacy Using Blockchain-Enabled Federated Learning in Fog Computing

Cited by 340 publications

References 32 publications

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

SS-ITS: secure scalable intelligent transportation systems

BlockEdge: Blockchain-Edge Framework for Industrial IoT Networks

Contact Info

Product

Resources

About