Research on Data Right Confirmation Mechanism of Federated Learning based on Blockchain

📅 2024-09-13
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address ambiguous data ownership and opaque benefit distribution in federated learning, this paper proposes a blockchain- and smart-contract-based mechanism for data rights assertion and fair reward allocation. Methodologically, it designs a Solidity smart contract system deployed on an Ethereum local environment, integrating hash-based evidence anchoring, distributed ledger recording, and a quantifiable contribution evaluation model for federated learning participants—enabling tamper-proof on-chain provenance of data contributions and rule-driven, automated reward distribution. The key innovation lies in the first systematic integration of blockchain immutability and smart contract self-execution into the end-to-end governance lifecycle of federated learning, establishing a fully auditable, end-to-end framework covering rights assertion, evidence preservation, and benefit allocation. Experimental results demonstrate the mechanism’s effectiveness in ensuring contribution record integrity, verifiability of distribution logic, and overall system feasibility.

Technology Category

Application Category

📝 Abstract
Federated learning can solve the privacy protection problem in distributed data mining and machine learning, and how to protect the ownership, use and income rights of all parties involved in federated learning is an important issue. This paper proposes a federated learning data ownership confirmation mechanism based on blockchain and smart contract, which uses decentralized blockchain technology to save the contribution of each participant on the blockchain, and distributes the benefits of federated learning results through the blockchain. In the local simulation environment of the blockchain, the relevant smart contracts and data structures are simulated and implemented, and the feasibility of the scheme is preliminarily demonstrated.
Problem

Research questions and friction points this paper is trying to address.

Protect data ownership in federated learning using blockchain
Ensure fair benefit distribution among federated learning participants
Validate feasibility through blockchain smart contract simulation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Blockchain-based federated learning data ownership
Smart contracts for benefit distribution
Decentralized contribution recording on blockchain
🔎 Similar Papers
No similar papers found.
X
Xiaogang Cheng
College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China
R
Ren Guo
College of Business Administration, Huaqiao University, Quanzhou 362021, China