Tao Zhang
School of Integrated Circuits and Electronic Information, Zibo Polytechnic University, Zibo 255300, Shandong, China.
*Corresponding author: Tao Zhang
Abstract
In the industrial Internet of Things environment, federated learning faces dual challenges of privacy leakage risk and resource constraints. Existing methods find it difficult to achieve an effective balance between heterogeneous data, limited communication and computing resources, and differentiated privacy requirements. This article systematically analyzes the privacy vulnerabilities of federated learning in the industrial Internet of Things, revealing the amplification effect of data heterogeneity on inference attacks and the limitations of existing protection methods. Furthermore, design privacy protection mechanisms for industrial scenarios, including hierarchical heterogeneous differential privacy noise adaptation, trusted execution environment security aggregation, dynamic allocation of privacy budgets, and adversarial robustness enhancement strategies. On this basis, a communication computing storage resource coupling constraint model is constructed to quantify the trade-off between privacy protection strength and training energy consumption, and a multi-objective optimization scheduling strategy and adaptive joint regulation protocol are proposed. The proposed mechanism provides a systematic theoretical framework for privacy, security, and resource collaboration in federated learning in the industrial Internet of Things.
References
[1] Ge T, Liu DZ, Li M. Industrial internet of things decentralized auditable privacy-preserving federated learning scheme. Softw Guide. 2026;25(5):21-27.
[2] Wang J, Qiao SM. Privacy-preserving data fusion algorithm for industrial internet of things. Intell IoT Technol. 2026;58(4):52-55. doi:10.26921/j.cnki.2096-6059.2026.04.012.
[3] Luo JB. Distributed intelligent sensing technology in industrial internet of things environment. Heilongjiang Sci. 2025;16(24):132-135.
[4] Liu X, Liu Y, Wang XZ, et al. SDP-FL: selective differential privacy federated learning framework for industrial internet of things. J Comput Appl Res. 2026;43(3):720-728.
doi:10.19734/j.issn.1001-3695.2025.07.0265.
[5] Zhang XY, Shi PZ, Gu CS, et al. Similarity-clustering personalized federated learning for industrial internet of things. Control Decis. 2026;41(4):1044-1054.
doi:10.13195/j.kzyjc.2025.0831.
[6] Zhang PY, He XB. CNN-LSTM-FedAvg-based industrial internet of things intrusion detection method. Comput Knowl Technol. 2025;21(19):97-99, 102.
doi:10.14004/j.cnki.ckt.2025.0957.
[7] Chen Q. Application of federated learning in industrial internet of things device security protection. China Broadband. 2025;21(8):61-63.
doi:10.20167/j.cnki.ISSN1673-7911.2025.08.21.
[8] Liu M, Xia YH, Zhao HT, et al. Federated learning for 6G industrial internet of things: from requirements and vision to challenges and opportunities. J Electron Inf Technol. 2024;46(12): 4335-4353.
[9] Lin FB, Wang C, Wu QX, et al. Blockchain-based heterogeneous federated ensemble learning system for industrial internet of things privacy protection. J Jiangxi Norm Univ (Nat Sci Ed). 2024;48(4):371-382. doi:10.16357/j.cnki.issn1000-5862.2024.04.08.
[10] Yang RZ, Xie XR, Teng YL, et al. Federated incremental learning algorithm and optimization based on information entropy in in-dustrial internet of things. J Electron Inf Technol. 2024;46(8):3146-3154.
[11] Xie CZ, Wang YH, Wang BD, et al. GRU-FedAdam-based industrial internet of things intrusion detection method. Netw Secur Data Gov. 2024;43(2):9-15.
doi:10.19358/j.cnki.issn2097-1788.2024.02.002.
How to cite this paper
Federated Learning Privacy Protection and Resource Collaborative Optimization Mechanism for Industrial Internet of Things
How to cite this paper: Tao Zhang. (2026) Federated Learning Privacy Protection and Resource Collaborative Optimization Mechanism for Industrial Internet of Things. Advances in Computer and Communication, 7(2), 86-90.
DOI: http://dx.doi.org/10.26855/acc.2026.06.005