TAP Rule Processing System Based on Federated Learning and Blockchain Technology

doi:10.3969/j.issn.1671-1122.2024.03.012

Abstract

Abstract:

Trigger-action programming (TAP) provides a convenient programming paradigm for users to interact with Internet of Things (IoT) devices. Analyzing user-defined TAP rules using machine learning techniques enables functionalities such as TAP rule recommendation and generation, and can improve user experience. However, TAP rules may contain personal privacy information, raising concerns about data upload and sharing. The paper proposes a TAP rule processing system based on federated learning and blockchain technology. Users can train TAP models locally without uploading private data. In order to solve the problem of centralized server single point failure and prevent malicious model parameter uploading, this article uses blockchain technology to improve the centralized TAP federated learning architecture. Users transmit locally updated model gradients to miners in the blockchain for anomaly detection and cross-validation. The mining committee integrated accumulated gradients from normal users to obtain a global model, connected as a block on the blockchain, available for download and use by normal users. The article uses a lightweight unsupervised non-negative matrix factorization method to verify the effectiveness of the proposed distributed learning architecture based on federated learning and blockchain. Experiments confirm that the architecture can effectively protect the privacy in TAP data, and that miners in the blockchain can well identify malicious model parameters, ensuring model stability.

Key words: trigger-action programming, non-negative matrix factorization, federated learning, blockchain

CLC Number:

TP309

XUE Mingzhu, HU Liang, WANG Ming, WANG Feng. TAP Rule Processing System Based on Federated Learning and Blockchain Technology[J]. Netinfo Security, 2024, 24(3): 473-485.

Figures/Tables 7

References 24

[1]	WANG Ming, XING Yongheng, WANG Feng. Unsupervised Matrix Factorization Based Trigger Action Programming Rules Recommendation[J]. Netinfo Security, 2023, 23(2): 96-103.
	王明, 邢永恒, 王峰. 基于无监督非负矩阵分解的TAP规则推荐[J]. 信息网络安全, 2023, 23(2): 96-103.
[2]	CHAI Di, WANG Leye, CHEN Kai, et al. Secure Federated Matrix Factorization[J]. IEEE Intelligent Systems, 2020, 36(5): 11-20. doi: 10.1109/MIS.2020.3014880 URL
[3]	SHIN H, KIM S, SHIM J, et al. Privacy Enhanced Matrix Factorization for Recommendation with Local Differential Privacy[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 30(9): 1770-1782. doi: 10.1109/TKDE.69 URL
[4]	KIM S, KIM J, KOO D, et al. Efficient Privacy-Preserving Matrix Factorization via Fully Homomorphic Encryption[C]// ACM. Proceedings of the 11th ACM on Asia Conference on Computer and Communications Security. New York: ACM, 2016: 617-628.
[5]	GILLIS N. The Why and How of Nonnegative Matrix Factorization[J]. Regularization, Optimization, Kernels, and Support Vector Machines, 2014, 12(257): 257-291.
[6]	YANG Qiang, LIU Yang, CHEN Tianjian, et al. Federated Machine Learning: Concept and Applications[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2019, 10(2): 1-19.
[7]	FERNANDES E, RAHMATI A, JUNG J, et al. Decentralized Action Integrity for Trigger-Action IoT Platforms[C]// Internet Society. Proceedings 2018 Network and Distributed System Security Symposium. San Diego: Network and Distributed System Security Symposium, 2018: 1-16.
[8]	CHEN Yunang, CHOWDHURY A R, WANG Ruizhe, et al. Data Privacy in Trigger-Action Systems[C]// IEEE. 2021 IEEE Symposium on Security and Privacy (SP). New York: IEEE, 2021: 501-518.
[9]	BREVE B, CIMINO G, DEUFEMIA V. Identifying Security and Privacy Violation Rules in Trigger-Action IoT Platforms with NLP Models[J]. IEEE Internet of Things Journal, 2022, 10(6): 5607-5622. doi: 10.1109/JIOT.2022.3222615 URL
[10]	MCMAHAN B, MOORE E, RAMAGE D, et al. Communication-Efficient Learning of Deep Networks from Decentralized Data[C]// PMLR.Artificial Intelligence and Statistics. New York: PMLR, 2017: 1273-1282.
[11]	SUN Rui, LI Chao, WANG Wei, et al. Research Progress of Blockchain-Based Federated Learning[J]. Journal of Computer Applications, 2022, 42(11): 3413-3420. doi: 10.11772/j.issn.1001-9081.2021111934
	孙睿, 李超, 王伟, 等. 基于区块链的联邦学习研究进展[J]. 计算机应用, 2022, 42(11): 3413-3420. doi: 10.11772/j.issn.1001-9081.2021111934
[12]	AONO Y, HAYASHI T, WANG Lihua, et al. Privacy-Preserving Deep Learning via Additively Homomorphic Encryption[J]. IEEE Transactions on Information Forensics and Security, 2017, 13(5): 1333-1345. doi: 10.1109/TIFS.2017.2787987 URL
[13]	KIM H, PARK J, BENNIS M, et al. Blockchained On-Device Federated Learning[J]. IEEE Communications Letters, 2019, 24(6): 1279-1283. doi: 10.1109/COML.4234 URL
[14]	BOGDANOV D, LAUR S, WILLEMSON J. Sharemind: A Framework for Fast Privacy-Preserving Computations[C]// ESORICS.Computer Security-ESORICS 2008: 13th European Symposium on Research in Computer Security. Heidelberg: Springer, 2008: 192-206.
[15]	NAKAMOTO S. Bitcoin: A Peer-to-Peer Electronic Cash System[EB/OL]. (2019-07-17)[2023-12-19]. https://bitcoin.org/bitcoin.pdf.
[16]	XIAO Yang, ZHANG Ning, LOU Wenjing, et al. A Survey of Distributed Consensus Protocols for Blockchain Networks[J]. IEEE Communications Surveys & Tutorials, 2020, 22(2): 1432-1465.
[17]	SAAD S M S, RADZI R Z R M. Comparative Review of the Blockchain Consensus Algorithm between Proof of Stake (PoS) and Delegated Proof of Stake (DPoS)[ J]. International Journal of Innovative Computing, 2020, 10(2): 27-32.
[18]	LAMPORT L, SHOSTAK R, PEASE M. The Byzantine Generals Problem[J]. ACM Transactions on Programming Languages and Systems, 1982, 4(3): 382-401. doi: 10.1145/357172.357176 URL
[19]	CASTRO M, LISKOV B. Practical Byzantine Fault Tolerance[C]// USENIX. Proceedings of the Third Symposium on Operating Systems Design and Implementation. Berkeley: USENIX, 1999: 173-186.
[20]	FURUKAWA J, LINDELL Y, NOF A, et al. High-Throughput Secure Three-Party Computation for Malicious Adversaries and an Honest Majority[C]// IACR. Annual International Conference on the Theory and Applications of Cryptographic Techniques. Heidelberg: Springer, 2017: 225-255.
[21]	KOGIAS E K, JOVANOVIC P, GAILLY N, et al. Enhancing Bitcoin Security and Performance with Strong Consistency via Collective Signing[C]// USENIX. 25th Usenix Security Symposium (Usenix Security 16). Berkeley: USENIX, 2016: 279-296.
[22]	ZHENG Zibin, XIE Shaoan, DAI Hongning, et al. Blockchain Challenges and Opportunities: A Survey[J]. International Journal of Web and Grid Services, 2018, 14(4): 352-375. doi: 10.1504/IJWGS.2018.095647 URL
[23]	ZHANG Yu, WEN Jiangtao. An IoT Electric Business Model Based on the Protocol of Bitcoin[C]// IEEE.2015 18th International Conference on Intelligence in Next Generation Networks. New York: IEEE, 2015: 184-191.
[24]	JIN Ming. Research on Key Technologies of Federated Learning Based on Blockchain[D]. Harbin:Harbin Engineering University, 2021.
	金明. 基于区块链的联邦学习关键技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2021.

	验证用户1	验证用户2	验证用户3	平均Error值
epoch_1_iteration_150	2.73	2.9	2.81	2.81
epoch_2_iteration_75	1.83	1.88	1.86	1.86
epoch_3_iteration_50	1.64	1.64	1.65	1.64
epoch_4_iteration_38	1.58	1.57	1.59	1.58
epoch_10_iteration_15	1.51	1.48	1.50	1.5
epoch_50_iteration_3	1.53	1.51	1.54	1.53
epoch_150_iteration_1	1.51	1.48	1.51	1.5
regular NMF	1.53	1.52	1.52	1.52

	测试用户1	测试用户2	测试用户3	平均Error值
epoch_10_iteration_15	1.57	1.45	1.47	1.49
regular NMF	1.62	1.45	1.54	1.53

随机改变位置的正数数量/个	测试1	测试2	测试3	测试4	测试5	测试6	测试7	测试8	平均值
100	30%	50%	30%	30%	40%	20%	40%	40%	35%
200	60%	60%	50%	80%	50%	70%	60%	60%	61%
300	60%	70%	70%	60%	70%	60%	70%	80%	67%
400	80%	70%	90%	100%	100%	70%	90%	90%	86%
500	90%	90%	90%	90%	90%	90%	90%	100%	91%