Blockchain-based federated learning with checksums to increase security in Internet of Things solutions

作     者：Prokop, Katarzyna Polap, Dawid Srivastava, Gautam Lin, Jerry Chun-Wei 

作者机构：Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44-100 Poland Dept. of Math and Computer Science Brandon University BrandonMBR7A 6A9 Canada Research Centre for Interneural Computing China Medical University Taichung Taiwan Western Norway University of Applied Sciences Bergen Norway Dept. of Computer Science and Math Lebanese American University Beirut1102 Lebanon 

出 版 物：《Journal of Ambient Intelligence and Humanized Computing》 (J. Ambient Intell. Humanized Comput.)

年 卷 期：2023年第14卷第5期

页      面：4685-4694页

核心收录：

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 070105[理学-运筹学与控制论] 0835[工学-软件工程] 081101[工学-控制理论与控制工程] 0701[理学-数学] 071101[理学-系统理论] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work is supported by the Rector proquality grant at the Silesian University of Technology  Poland No. 09/010/RGJ22/0067 

主　　题：Blockchain 

摘      要：Federated learning is becoming a practical solution for machine learning (ML) in industry. This is due to the possibility of implementing artificial intelligence (AI) systems and training its models on private data sets. However, this is not an ideal solution as it is possible to manipulate or even intercept the model during its transmission between the server and workers. In this paper, we propose a solution to ensure the security of the model transmitted between units in FL. The given model is encrypted with AES, DES, RSA algorithms, then a checksum is determined. This checksum with a private key is stored as a transaction on a blockchain. In the case of sending the model and its modification, the recipient can easily verify whether it is correct. The proposed solution has been described, tested, and compared to indicate its advantages and disadvantages. Conducted experiments were based on analyzing the communication time between participants, the accuracy of machine learning models, and attack detection. In terms of attack detection on the blockchain, we reached 81% thanks to the checksum mechanism. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.