测试技术学报2024，Vol.38Issue(4)：345-353,9.DOI:10.3969/j.issn.1671-7449.2024045
基于声誉机制的区块链赋能多无人机系统联邦学习研究
Research on Federated Learning of Blockchain Enabled Multi UAV System Based on Reputation Mechanism
摘要
Abstract
Drones equipped with detectors can be used for applications such as air quality prediction.Fed-erated learning empowers multi-drone systems to face challenges such as single point of failure,malicious attacks,and difficulty in achieving fair incentives.This article studies a reputation based blockchain enabled federated learning scheme for multi-drone systems.By automatically executing tasks through blockchain-based smart contracts,local model quality is evaluated based on reputation values,and mali-cious drones are identified and removed based on reputation thresholds.Sparse the global model based on reputation value to achieve fair distribution of model profits,and comprehensively consider reputation value and data volume to reward honest drones with corresponding costs.The simulation verified through the MNIST dataset that the algorithm proposed in this paper has higher accuracy than the FedAVG algo-rithm,and can identify and expel malicious drones under different proportions,achieving a fair distribution of model profits and total budget.关键词
声誉值/无人机/联邦学习/智能合约/区块链Key words
reputation value/unmanned aerial vehicles/federated learning/smart contracts/blockchain分类
信息技术与安全科学引用本文复制引用
郭禹江,张志才..基于声誉机制的区块链赋能多无人机系统联邦学习研究[J].测试技术学报,2024,38(4):345-353,9.基金项目
山西省基础研究计划自然科学研究面上资助项目(202103021224024) （202103021224024）
山西省基础研究计划青年科学研究资助项目(20210302123021) （20210302123021）
山西省重点研发计划资助项目(202202020101004) （202202020101004）
