摘要
零散、孤立的海量数据形成“数据孤岛”使得数据无法交互和连接,如何在保护原始数据隐私的前提下安全有效地共享数据中的知识信息已成为热点研究问题。基于以上内容,提出了一种基于区块链的联邦蒸馏数据共享模型(BFDS)。区别于中心化架构,采用区块链联合多参与方组建教师网络,实现分布式协同工作;通过交换蒸馏输出的方式,传递数据中的知识信息,联合训练轻量化模型;提出了一种多权重节点可信评估算法,调用智能合约分配权重并生成可溯源全局软标签,降低因参与方质量差异而产生的负向影响。实验结果表明,BFDS模型能联合多参与方安全可信共享数据知识,协同蒸馏训练模型,降低了模型的部署成本;所提出的多权重节点评估算法能有效减小低质量节点的负向影响,提高了全局软标签的质量与安全性。
The privacy of raw data makes it difficult to be directly shared among multiple participants.The issue of data security sharing and privacy-preserving has become a hot research topic.To solve this problem,this paper proposes a blockchain-based bederated distillation data sharing model(BFDS).It utilizes blockchain to form a collaborative teacher network with multiple participants.Through distilled output exchange,the knowledge from complex teacher networks is transferred and used to train lightweight models.A novel multi-weight node trust evaluation algorithm is proposed that uses smart contracts to generate traceable global soft labels.It can reduce the negative impact caused by quality differences among participants.Experimental results show that BFDS can collaborate with multiple parties to share data knowledge reliably,distill training models collaboratively,and reduce model deployment costs.The proposed algorithm can effectively reduce the negative impact of low-quality nodes and improve the quality and security of global soft labels.
作者
刘炜
刘宇昭
唐琮轲
王媛媛
佘维
田钊
LIU Wei;LIU Yuzhao;TANG Congke;WANG Yuanyuan;SHE Wei;TIAN Zhao(School of Cyber Science and Engineering,Zhengzhou University,Zhengzhou 450002,China;Henan Key Laboratory of Network Cryptography Technology(Information Engineering University),Zhengzhou 450000,China;Zhengzhou Key Laboratory of Blockchain and Data Intelligence(Zhengzhou University),Zhengzhou 450000,China;Songshan Laboratory,Zhengzhou 450000,China;State Grid Henan Electric Power Company,Xuchang,Henan 461000,China)
出处
《计算机科学》
CSCD
北大核心
2024年第3期39-47,共9页
Computer Science
基金
河南省高校科技创新人才支持计划(21HASTIT031)
河南省网络密码技术重点实验室研究课题(LNCT2022-A04)
河南省高等学校重点科研项目(24A520045)
嵩山实验室预研项目(YYYY022022003)。
关键词
区块链
知识蒸馏
数据共享
智能合约
Blockchain
Knowledge distillation
Data sharing
Smart contracts
