• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.958-979
• /
• 2023

Due to laws, regulations, privacy, etc., between 70-90 percent of providers do not share medical data, forming a "data island". It is essential to collaborate across multiple institutions without sharing patient data. Most existing methods adopt distributed learning and centralized federal architecture to solve this problem, but there are problems of resource heterogeneity and data heterogeneity in the practical application process. This paper proposes a collaborative deep learning modelling method based on the blockchain network. The training process uses encryption parameters to replace the original remote source data transmission to protect privacy. Hyperledger Fabric blockchain is adopted to realize that the parties are not restricted by the third-party authoritative verification end. To a certain extent, the distrust and single point of failure caused by the centralized system are avoided. The aggregation algorithm uses the FedProx algorithm to solve the problem of device heterogeneity and data heterogeneity. The experiments show that the maximum improvement of segmentation accuracy in the collaborative training mode proposed in this paper is 11.179% compared to local training. In the sequential training mode, the average accuracy improvement is greater than 7%. In the parallel training mode, the average accuracy improvement is greater than 8%. The experimental results show that the model proposed in this paper can solve the current problem of centralized modelling of multicenter data. In particular, it provides ideas to solve privacy protection and break "data silos", and protects all data.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.105-117
• /
• 2019

Bitcoin, which can be classified as a cryptocurrency, has attracted attention from various industries because it is an innovative digital currency and the beginning of a Blockchain system. However, as the research on Bitcoin progressed, several security vulnerabilities and possible attacks were analyzed. Among them, the security problem caused by the transparency of the Blockchain database prevents the Blockchain system from being applied to various fields. This vulnerability is further classified as the weak anonymity of participating nodes and privacy problem due to disclosure of transaction details. In recent years, several countermeasures have been developed against these vulnerabilities. In this paper, we first describe the main features of the public and private Blockchain, and explain privacy, unlinkability and anonymity. And, three public Blockchain platforms, Dash, Zcash and Monero which are derived from Bitcoin, and Hyperledger Fabric which is a private Blockchain platform, are examined. And we analyze the operating principles of the protocols applied on each platform. In addition, we classify the applied technologies into anonymity and privacy protection in detail, analyze the advantages and disadvantages, and compare the features and relative performance of the platforms based on the computational speed of the applied cryptographic mechanisms.