Open Access iconOpen Access

ARTICLE

crossmark

Transparent and Accountable Training Data Sharing in Decentralized Machine Learning Systems

Siwan Noh1, Kyung-Hyune Rhee2,*

1 Industrial Science Technology Research Center, Pukyong National University, Busan, 48513, South Korea
2 Division of Computer Engineering, Pukyong National University, Busan, 48513, South Korea

* Corresponding Author: Kyung-Hyune Rhee. Email: email

(This article belongs to the Special Issue: Innovative Security for the Next Generation Mobile Communication and Internet Systems)

Computers, Materials & Continua 2024, 79(3), 3805-3826. https://doi.org/10.32604/cmc.2024.050949

Abstract

In Decentralized Machine Learning (DML) systems, system participants contribute their resources to assist others in developing machine learning solutions. Identifying malicious contributions in DML systems is challenging, which has led to the exploration of blockchain technology. Blockchain leverages its transparency and immutability to record the provenance and reliability of training data. However, storing massive datasets or implementing model evaluation processes on smart contracts incurs high computational costs. Additionally, current research on preventing malicious contributions in DML systems primarily focuses on protecting models from being exploited by workers who contribute incorrect or misleading data. However, less attention has been paid to the scenario where malicious requesters intentionally manipulate test data during evaluation to gain an unfair advantage. This paper proposes a transparent and accountable training data sharing method that securely shares data among potentially malicious system participants. First, we introduce a blockchain-based DML system architecture that supports secure training data sharing through the IPFS network. Second, we design a blockchain smart contract to transparently split training datasets into training and test datasets, respectively, without involving system participants. Under the system, transparent and accountable training data sharing can be achieved with attribute-based proxy re-encryption. We demonstrate the security analysis for the system, and conduct experiments on the Ethereum and IPFS platforms to show the feasibility and practicality of the system.

Keywords


Cite This Article

APA Style
Noh, S., Rhee, K. (2024). Transparent and accountable training data sharing in decentralized machine learning systems. Computers, Materials & Continua, 79(3), 3805-3826. https://doi.org/10.32604/cmc.2024.050949
Vancouver Style
Noh S, Rhee K. Transparent and accountable training data sharing in decentralized machine learning systems. Comput Mater Contin. 2024;79(3):3805-3826 https://doi.org/10.32604/cmc.2024.050949
IEEE Style
S. Noh and K. Rhee, "Transparent and Accountable Training Data Sharing in Decentralized Machine Learning Systems," Comput. Mater. Contin., vol. 79, no. 3, pp. 3805-3826. 2024. https://doi.org/10.32604/cmc.2024.050949



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 249

    View

  • 98

    Download

  • 0

    Like

Share Link