A blockchainized privacy-preserving support vector machine classification on mobile crowd sensed data

Smahi, Abla; Xia, Qi; Xia, Hu; Nantogma, Sulemana; Fateh, Ahmed Ameen; Gao, Jianbin; Du, Xiaojiang; Guizani, Mohsen

doi:10.1016/j.pmcj.2020.101195

Cited by 23 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many different types of privacy-preserving SVM training and classification with cloud or blockchain-based services. [20][21][22]…”

Section: Related Workmentioning

confidence: 99%

Privacy preserving support vector machine based on federated learning for distributed IoT‐enabled data analysis

Chen,

Hsu,

Xie

et al. 2024

Computational Intelligence

View full text Add to dashboard Cite

In a smart city, IoT devices are required to support monitoring of normal operations such as traffic, infrastructure, and the crowd of people. IoT‐enabled systems offered by many IoT devices are expected to achieve sustainable developments from the information collected by the smart city. Indeed, artificial intelligence (AI) and machine learning (ML) are well‐known methods for achieving this goal as long as the system framework and problem statement are well prepared. However, to better use AI/ML, the training data should be as global as possible, which can prevent the model from working only on local data. Such data can be obtained from different sources, but this induces the privacy issue where at least one party collects all data in the plain. The main focus of this article is on support vector machines (SVM). We aim to present a solution to the privacy issue and provide confidentiality to protect the data. We build a privacy‐preserving scheme for SVM (SecretSVM) based on the framework of federated learning and distributed consensus. In this scheme, data providers self‐organize and obtain training parameters of SVM without revealing their own models. Finally, experiments with real data analysis show the feasibility of potential applications in smart cities. This article is the extended version of that of Hsu et al. (Proceedings of the 15th ACM Asia Conference on Computer and Communications Security. ACM; 2020:904‐906).

show abstract

“…There are many different types of privacy-preserving SVM training and classification with cloud or blockchain-based services. [20][21][22]…”

Section: Related Workmentioning

confidence: 99%

Privacy preserving support vector machine based on federated learning for distributed IoT‐enabled data analysis

Chen,

Hsu,

Xie

et al. 2024

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…(Lee et al 2011 ). On the other hand, although QR code payment and other mobile payment systems are thought to contain some security vulnerabilities, these difficulties are overcome thanks to blockchain technologies (Smahi et al 2020 ). For this reason, it is important for banks to develop and continuously improve risk prevention and control mechanism in QR code m-payment in order to prevent these attempts (The People’s Bank of China 2017 ).…”

Section: Theoretical Background and Hypotheses Developmentmentioning

confidence: 99%

QR code m-payment from a customer experience perspective

Eren

2022

J Financ Serv Mark

View full text Add to dashboard Cite

This study aimed to examine the effect of the quality dimensions of information system success model (ISSM), perceived risk, perceived transaction speed, and optimistic perspective on Quick Response (QR) code mobile payment (m-payment) experience. For this purpose, a survey was conducted in Turkey involving 207 adults who had experienced the QR code m-payment method. Partial least squares structural equation modeling (PLS-SEM) was used to investigate the relations between the variables. Research results showed that information quality, system quality, perceived transaction speed, and optimism significantly affected customer experience. However, service quality and perceived risk regarding QR code m-payment had no impact on customer experience. This study tried to reveal behavioral intentions of users in future by bringing together the concepts of ISSM and marketing, examining the QR code m-payment customer experience in the pandemic period with an integrative approach. In this context, the research has theoretical implications that extend ISSM toward improving technology-based financial services and omnichannel marketing.

show abstract

“…SMPC has been applied to the fields of secure voting [17], data sharing in the medical industry [18], blockchains [19], and data mining [20]. However, the considerable computational costs of conducting sophisticated assignments using SMPC protocols prevents further applications of SMPC.…”

Section: A Indices/setsmentioning

confidence: 99%

Fully Privacy-Preserving Distributed Optimization Based on Secret Sharing

Tian¹,

Guo²,

Sun³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the increasing development of smart grid, multiparty cooperative computation between several entities has become a typical characteristic of modern energy systems. Traditionally, data exchange among parties is inevitable, rendering how to complete multiparty collaborative optimization without exposing any private information a critical issue. This paper proposes a fully privacy-preserving distributed optimization framework based on secure multiparty computation (SMPC) secret sharing protocols. The framework decomposes the collaborative optimization problem into a master problem and several subproblems. The process of solving the master problem is executed in the SMPC framework via the secret sharing protocols among agents. The relationships of agents are completely equal, and there is no privileged agent or any third party. The process of solving subproblems is conducted by agents individually. Compared to the traditional distributed optimization framework, the proposed SMPC-based framework can fully preserve individual private information. Exchanged data among agents are encrypted and no private information disclosure is assured. Furthermore, the framework maintains a limited and acceptable increase in computational costs while guaranteeing optimality. Case studies are conducted to demonstrate the principle of secret sharing and verify the feasibility and scalability of the proposed methodology. <br>

show abstract

A blockchainized privacy-preserving support vector machine classification on mobile crowd sensed data

Cited by 23 publications

References 26 publications

Privacy preserving support vector machine based on federated learning for distributed IoT‐enabled data analysis

Privacy preserving support vector machine based on federated learning for distributed IoT‐enabled data analysis

QR code m-payment from a customer experience perspective

Fully Privacy-Preserving Distributed Optimization Based on Secret Sharing

Contact Info

Product

Resources

About