Blockchain based adaptive federated learning in computational power network

LIU Tianrui; WANG Lianhai; WANG Qizheng; XU Shujiang; ZHANG Shuhui; WANG Yingxiaochun

doi:10.11959/j.issn.2096-109x.2024045

您当前的位置：

首页 >

文章列表页 >

Blockchain based adaptive federated learning in computational power network

Papers | 更新时间：2024-08-14

- Blockchain based adaptive federated learning in computational power network
- Chinese Journal of Network and Information Security Vol. 10, Issue 3, Pages: 130-142(2024)
- 作者机构：
  
  1.齐鲁工业大学（山东省科学院）山东省计算中心（国家超级计算济南中心）；算力互联网与信息安全教育部重点实验室，山东济南 250014
  2.山东省计算机网络重点实验室，山东省基础科学研究中心（计算机科学），山东济南 250014
- 作者简介：
- 基金信息：
  
  The Shandong Provincial Key Research and Development Program(2021CXGC010107);The National Natural Science Foundation of China(62102209);The New 20 Project of Higher Education of Jinan(202228017);The Taishan Scholars Program(tsqn202312231)
- DOI：10.11959/j.issn.2096-109x.2024045
  CLC： TP393
- Received：29 February 2024，
  
  Revised：2024-04-26，
  
  Published：25 June 2024
- 稿件说明：
移动端阅览
刘天瑞, 王连海, 王启正, 等. 算力网络环境下基于区块链的自适应联邦学习[J]. 网络与信息安全学报, 2024, 10(3): 130-142.

LIU T R, WANG L H, WANG Q Z, et al. Blockchain based adaptive federated learning in computational power network[J]. Chinese Journal of Network and Information Security, 2024, 10(3): 130-142.
刘天瑞, 王连海, 王启正, 等. 算力网络环境下基于区块链的自适应联邦学习[J]. 网络与信息安全学报, 2024, 10(3): 130-142. DOI： 10.11959/j.issn.2096-109x.2024045.

LIU T R, WANG L H, WANG Q Z, et al. Blockchain based adaptive federated learning in computational power network[J]. Chinese Journal of Network and Information Security, 2024, 10(3): 130-142. DOI： 10.11959/j.issn.2096-109x.2024045.

摘要

算力网络旨在深度融合算力资源与网络资源，实现对泛在离散部署的海量数据和异构资源的高效利用。为了应对算力网络中复杂的多中心计算协同和数据隐私安全的要求，联邦学习在隐私保护和边缘算力资源利用等方面有着先天的优势。然而，基于算力边缘服务器的高度异构和广泛分布，算力网络环境下的联邦学习仍然存在一定的困难。一方面，算力网络中海量边缘服务器之间存在的数据异质性会引起非独立同分布问题，导致联邦学习中局部模型的更新偏离全局最优值。另一方面，由于不同边缘服务器的数据质量存在差异，生成低质量的局部模型会显著影响训练效果。为了解决上述问题，提出了基于区块链的自适应联邦学习（AWFL-BC，adaptive weight federated learning-blockchain）方案。通过智能合约计算不同边缘服务器的数据分布距离，生成相似度矩阵指导聚合。同时，设计了一种自适应权重聚合算法，以减轻由数据质量差异引起的模型性能和稳定性下降，从而提升模型的准确率，加速模型收敛。最后，结合区块链技术加强了安全保障机制，可有效防止投毒攻击与推理攻击。在3个公有标准数据集上进行的综合实验表明，与最先进的方法相比，AWFL-BC实现了更高的模型准确率，且模型收敛速度更快。

Abstract

The computational power network was aimed to deeply integrate arithmetic resources and network resources

achieving efficient utilization of massive data and heterogeneous resources in ubiquitous discrete deployment. To cope with the complicated multicenter computing collaboration and requirements for data privacy and security in computational power networks

federated learning was recognized for its inherent advantages in privacy protection and edge arithmetic resource utilization. However

federated learning in the computational power network environment faced certain difficulties due to the highly heterogeneous and widely distributed arithmetic edge servers. On one hand

the heterogeneity of data among the massive edge servers in the computational power network caused the Non-IID problem

leading to the deviation of the local model update from the global optimum in federated learning. On the other hand

the generation of low-quality local models could significantly affect the training effect due to the differences in data quality among different edge servers. To solve the above problems

a blockchain-based adaptive federated learning framework AWFL-BC (adaptive weight federated learning-blockchain) was proposed. Initially

the data distribution distances of different edge servers were calculated through smart contracts to generate a similarity matrix that guided aggregation. Concurrently

an adaptive weight aggregation algorithm was designed to alleviate the decrease in model performance and stability caused by differences in data quality

thereby improving the accuracy of the model and accelerating model convergence. Finally

the integration of blockchain technology strengthened the security mechanism

effectively preventing poisoning attacks and inference attacks. Comprehensive experiments on three public standard datasets show that AWFL-BC achieves higher model accuracy and faster model convergence compared to state-of-the-art methods.

关键词

Keywords

references

RODRIGUEZ I , MOGENSEN R S , SCHJØRRING A , et al . 5G swarm production: advanced industrial manufacturing concepts enabled by wireless automation [J ] . IEEE Communications Magazine , 2021 , 59 ( 1 ): 48 - 54 .

LIAO W X , LUO C Q , SALINAS S , et al . Efficient secure outsourcing of large-scale convex separable programming for big data [J ] . IEEE Transactions on Big Data , 2019 , 5 ( 3 ): 368 - 378 .

SUN Y K , LEI B , LIU J L , et al . Computing power network: a survey [EB ] . arXiv preprint arXiv: 2210. 06080 , 2022 .

梁芳 , 佟恬 , 马贺荣 , 等 . 东数西算下算力网络发展分析 [J ] . 信息通信技术与政策 , 2022 ( 11 ): 79 - 83 .

LIANG F , TONG T , MA H R , et al . Analysis of the development of the computing power network under east-data-west-computing project [J ] . Information and Communications Technology and Policy , 2022 ( 11 ): 79 - 83 .

SAVAZZI S , NICOLI M , BENNIS M , et al . Opportunities of federated learning in connected, cooperative, and automated industrial systems [J ] . IEEE Communications Magazine , 2021 , 59 ( 2 ): 16 - 21 .

VAHIDIAN S , MORAFAH M , LIN B . Personalized federated learning by structured and unstructured pruning under data heterogeneity [C ] // Proceedings of the 2021 IEEE 41st International Conference on Distributed Computing Systems Workshops (ICDCSW) . Piscataway : IEEE Press , 2021 : 27 - 34 .

MCMAHAN H B , MOORE E , RAMAGE D , et al . Communication-efficient learning of deep networks from decentralized data [EB ] . arXiv Preprint , 2016 , arXiv: .1602.05629 .

LI T , SAHU A K , TALWALKAR A , et al . Federated learning: challenges, methods, and future directions [J ] . IEEE Signal Processing Magazine , 2020 , 37 ( 3 ): 50 - 60 .

YUAN X T , LI P . On convergence of FedProx: local dissimilarity invariant bounds, non-smoothness and beyond [EB ] . arXiv Preprint arXiv: 2206.05187 , 2022 .

LI X X , JIANG M R , ZHANG X F , et al . FedBn: federated learning on non-IID features via local batch normalization [EB ] . arXiv Preprint arXiv: 2102.07623 , 2021 .

WANG J Y , LIU Q H , LIANG H , et al . Tackling the objective inconsistency problem in heterogeneous federated optimization [EB ] . arXiv Preprint , 2020 , arXiv: 2007.07481 .

ZHAO Y , LI M , LAI L Z , et al . Federated learning with non-IID data [EB ] . arXiv Preprint , 2018 , arXiv: 1806.00582 .

张泽辉 , 李庆丹 , 富瑶 , 等 . 面向非独立同分布数据的自适应联邦深度学习算法 [J ] . 自动化学报 , 2023 , 49 ( 12 ): 2493 - 2506 .

ZHANG Z H , LI Q D , FU Y , et al . Adaptive federated deep learning with non-IID data [J ] . Acta Automatica Sinica , 2023 , 49 ( 12 ): 2493 - 2506 .

GEYER R C , KLEIN T , NABI M . Differentially private federated learning: a client level perspective [EB ] . arXiv Preprint arXiv: 1712.07557 , 2017 .

CAI J P , LIU X M , YE Q Q , et al . A federated learning framework based on differentially private continuous data release [J ] . IEEE Transactions on Dependable and Secure Computing , 2024 , ( 99 ): 1 - 16 .

ZHOU F , CONG G J . On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimization [EB ] . arXiv Preprint arXiv: 1708. 01012 . 2017 .

ZHENG Q Q , CHEN S X , LONG Q , et al . Federated f-differential privacy [EB ] . arXiv Preprint arXiv: 2102.11158 , 2021 .

YANG Z Q , ZHANG Y G , ZHENG Y , et al . FedFed: feature distillation against data heterogeneity in federated learning [EB ] . arXiv Ppreprint arXiv: 2310.05077 , 2023 .

侍江烽 , 冯宝 , 陈业航 , 等 . 基于自适应聚合权重联邦学习的肺结节CT图像分类 [J ] . 激光与光电子学进展 , 2023 , 60 ( 22 ): 3788 /LOP223027.

SHI J F , FENG B , CHEN Y H , et al . Lung nodule CT image classification based on adaptive aggregate weight federated learning [J ] . Laser & Optoelectronics Progress , 2023 , 60 ( 22 ): 3788 /LOP223027.

WANG Z L , HU Q . Blockchain-based federated learning: a comprehensive survey [EB ] . arXiv Preprint arXiv: 2110. 02182 ,. 2021.

应作斌 , 方一晨 , 张怡文 . 动态聚合权重的隐私保护联邦学习框架 [J ] . 网络与信息安全学报 , 2022 , 8 ( 5 ): 56 - 65 .

YING Z B , FANG Y C , ZHANG Y W . Privacy-preserving federated learning framework with dynamic weight aggregation [J ] . Chinese Journal of Network and Information Security , 2022 , 8 ( 5 ): 56 - 65 .

朱建明 , 张沁楠 , 高胜 , 等 . 基于区块链的隐私保护可信联邦学习模型 [J ] . 计算机学报 , 2021 , 44 ( 12 ): 2464 - 2484 .

ZHU J M , ZHANG Q N , GAO S , et al . Privacy preserving and trustworthy federated learning model based on blockchain [J ] . Chinese Journal of Computers , 2021 , 44 ( 12 ): 2464 - 2484 .

KIM Y J , HONG C S . Blockchain-based node-aware dynamic weighting methods for improving federated learning performance [C ] // Proceedings of the 2019 20th Asia-Pacific Network Operations and Management Symposium (APNOMS) . Piscataway : IEEE Press , 2019 : 1 - 4 .

LI Y Z , CHEN C , LIU N , et al . A blockchain-based decentralized federated learning framework with committee consensus [J ] . IEEE Network , 2021 , 35 ( 1 ): 234 - 241 .

DAEMEN J , RIJMEN V . REIJNDAEL: The advanced encryption standard [J ] . Dr. Dobb's Journal: Software Tools for the Professional Programmer , 2001 , 26 ( 3 ): 137 - 139 .

CORON J S , DODIS Y , MALINAUD C , et al . Merkle-Damgård revisited: How to construct a hash function [C ] // Advances in Cryptology–CRYPTO 2005: 25th Annual International Cryptology Conference , Santa Barbara, California, USA, August 14 - 18 , 2005 . Proceedings 25 . Springer Berlin Heidelberg, 2005: 430 - 448 .

LU W , WANG J D , CHEN Y Q , et al . Personalized federated learning with adaptive batchnorm for healthcare [J ] . IEEE Transactions on Big Data , 2022 , PP(99): 1.

MUÑOZ-GONZÁLEZ L , BIGGIO B , DEMONTIS A , et al . Towards poisoning of deep learning algorithms with back-gradient optimization [C ] // Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security . New York : ACM , 2017 : 27 - 38 .

MELIS L , SONG C Z , DE CRISTOFARO E , et al . Exploiting unintended feature leakage in collaborative learning [C ] // Proceedings of the 2019 IEEE Symposium on Security and Privacy (SP) . Piscataway : IEEE Press , 2019 : 691 - 706 .

YANG J C , SHI R , WEI D L , et al . MedMNIST v2 - a large-scale lightweight benchmark for 2D and 3D biomedical image classification [J ] . Scientific Data , 2023 , 10 : 41 .

YUROCHKIN M , AGARWAL M , GHOSH S , et al . Bayesian nonparametric federated learning of neural networks [EB ] . arXiv Preprint , arXiv: 1905.12022 , 2019 .

LECUN Y , BOTTOU L , BENGIO Y , et al . Gradient-based learning applied to document recognition [J ] . Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Double layer federated security learning architecture for artificial intelligence of things

Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain

Survey of federated learning research

DP-FedDRC: differentially private personalized federated learning to alleviate dimension collapse

Ring adaptor signature scheme based on SM2 digital signature algorithm

Related Author

ZHENG Chengbo

YAN Haonan

FU Caili

ZHANG Dong

LI Hui

WANG Bin

Ming YANG

Xuexian HU

Related Institution

School of Cyber Engineering, Xidian University

Hangzhou Hikvision Digital Technology Co.,Ltd

National Computer Network Emergency Response Technical Team/Coordination Center of China(CNCERT/CC)

Zhejiang Key Laboratory of Artificial Intelligence of Things（AIoT）Network and Data Security

Strategic Support Force Information Engineering University

⁰