Highly efficient federated learning with strong privacy preservation in cloud computing

Chen, Fang; Guo, Yuanbo; Wang, Na; Ju, Ankang

doi:10.1016/j.cose.2020.101889

Cited by 84 publications

(40 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Federated learning has been suggested as a distributed platform to overcome these limitations, where multiple customers collectively train a machine learning model without partitioning their individual datasets. Fang et al [48] designed a federated learning scheme with strong privacy preservation, named HFWP, for For enhancing cloud computing-based 5G heterogeneous network, Wei et al [77] designed a federated learning scheme based on end-edge-cloud cooperation. Within this scheme, the nodes that are equipped with mechanisms for attack detection are deployed in the end, edge, and cloud of the 5G heterogeneous network.…”

Section: F Secure Cloud Computingmentioning

confidence: 99%

Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis

Ferrag¹,

et al. 2021

View full text Add to dashboard Cite

In this article, we present a comprehensive study with an experimental analysis of federated deep learning approaches for cyber security in the Internet of Things (IoT) applications. Specifically, we first provide a review of the federated learning-based security and privacy systems for several types of IoT applications, including, Industrial IoT, Edge Computing, Internet of Drones, Internet of Healthcare Things, Internet of Vehicles, etc. Second, the use of federated learning with blockchain and malware/intrusion detection systems for IoT applications is discussed. Then, we review the vulnerabilities in federated learning-based security and privacy systems. Finally, we provide an experimental analysis of federated deep learning with three deep learning approaches, namely, Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and Deep Neural Network (DNN). For each deep learning model, we study the performance of centralized and federated learning under three new real IoT traffic datasets, namely, the Bot-IoT dataset, the MQTTset dataset, and the TON_IoT dataset. The goal of this article is to provide important information on federated deep learning approaches with emerging technologies for cyber security. In addition, it demonstrates that federated deep learning approaches outperform the classic/centralized versions of machine learning (non-federated learning) in assuring the privacy of IoT device data and provide the higher accuracy in detecting attacks.

show abstract

Section: F Secure Cloud Computingmentioning

confidence: 99%

Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis

Ferrag¹,

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Since its inception, Federated Learning is evolving, accommodating different application scenarios and having even stronger privacy focus. From Blockchain integration [116] to deployment in wireless networks [117], a large focus is on performance and privacy improvements [118]- [122]. For instance, Niu et al [122] proposed a framework where clients download only portions of the model, train it locally, and then upload the renewed version.…”

Section: E Privacy Technologies For the Cloudmentioning

confidence: 99%

Privacy in the Cloud: A Survey of Existing Solutions and Research Challenges

2021

View full text Add to dashboard Cite

“…Cloud providers are commonly seen as "honest-butcurious" [26]. To protect data in those environments, some common methods include, searchable encryption [27]- [29] and pseudonymity [30], [31] schemes.…”

Section: Introductionmentioning

confidence: 99%

A Performant Protocol for Distributed Health Records Databases

2021

View full text Add to dashboard Cite

Electronic Health Records (EHR) have a distributed nature and can be managed by distinct affinity domains. Sharing patient health information across distinct organisations helps to deliver a wellinformed diagnosis, improving the quality of healthcare service. The federation of those information systems can take the form of a distributed database where data are partitioned and possibly replicated across distinct computational systems. However, the benefits of having a distributed system, such as consistency, availability, and data protection, are mostly absent. This article proposes a distributed database consensus protocol designed to improve the performance of EHR insertion operations, a particularly critical issue in medical imaging cases due to the data volume. It explores the personal and non-transferable nature of EHR and the proposed methodology reduces the data contention through data isolation, improving the overall retrieval performance and detection of misbehaving parties. Furthermore, the proposal follows the recent European General Data Protection Regulation (GDPR), which states that appropriate mechanisms should be used in order to protect data against accidental loss, destruction, or damage, using appropriate technical or organisational measures.INDEX TERMS blockchain, consensus protocol, distributed ledger, distributed databases, electronic health records

show abstract

Highly efficient federated learning with strong privacy preservation in cloud computing

Cited by 84 publications

References 7 publications

Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis

Federated Deep Learning for Cyber Security in the Internet of Things: Concepts, Applications, and Experimental Analysis

Privacy in the Cloud: A Survey of Existing Solutions and Research Challenges

A Performant Protocol for Distributed Health Records Databases

Contact Info

Product

Resources

About