Research on Privacy Leakage Defense Mechanism and Ethical Governance Path under Federated Learning Framework
Main Article Content
Abstract
Federated learning, as the core paradigm of distributed machine learning, implements multi-party collaborative modeling with a “data stationary, model dynamic” architecture, providing a technical path for solving the dual dilemma of data silos and privacy protection. However, the distributed nature and parameter interaction mechanism of federated learning pose new privacy leakage risks such as gradient reversal, member inference, and model poisoning. Existing defense mechanisms suffer from imbalanced privacy performance trade-offs, insufficient cross scenario adaptability, and lack of a systematic ethical governance framework.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
S. Umar, A. Alagha, R. Mizouni, et al., “A two-sided client-server matching mechanism for resilient Federated Learning,” Journal of Network and Computer Applications, vol. 250, Art. no. 104476, 2026, doi: 10.1016/j.jnca.2026.104476.
J. Zhang, X. Zhan, X. Wang, et al., “Federated learning-based user behavior prediction model for rural live e-commerce,” Alexandria Engineering Journal, vol. 141, pp. 413–427, 2026, doi: 10.1016/j.aej.2026.03.027.
X. Lai, Z. Zhang, and S. Zheng, “FLAME: Federated learning on heterogeneous and long-tailed data via adaptive multi-faceted feature embeddings,” Future Generation Computer Systems, vol. 182, Art. no. 108488, 2026, doi: 10.1016/j.future.2026.108488.
J. Zheng, X. Shen, S. Zhao, et al., “FedCDC: Communication-efficient clustered federated learning for het-erogeneous IoT edge networks,” Internet of Things, vol. 37, Art. no. 101925, 2026, doi: 10.1016/j.iot.2026.101925.
E. Beltrán M T, E. Gash, G. Bovet, et al., “Asynchronous Cache-based Aggregation with Fairness and Filtering for Decentralized Federated Learning,” Computer Networks, vol. 281, Art. no. 112225, 2026, doi: 10.1016/j.comnet.2026.112225.
A. Lameesa, M. Alam B S, S. Ahmed F, et al., “Federated learning for sustainable IoT: Decentralized intelligence and energy-efficient applications,” Energy Reports, vol. 15, Art. no. 109145, 2026, doi: 10.1016/j.egyr.2026.109145.
R. Chen, D. Bao, N. Lu, et al., “Robust federated learning for dynamic and heterogeneous environments: an adaptive client selection approach,” Expert Systems With Applications, vol. 318, Art. no. 131992, 2026, doi: 10.1016/j.eswa.2026.131992.
L. Feng, M. Liu, Z. Jing, et al., “A privacy-preserving and byzantine-robust consensus for blockchain Federated Learning,” Engineering Applications of Artificial Intelligence, vol. 175, Art. no. 114589, 2026, doi: 10.1016/j.engappai.2026.114589.
K. Singh P, M. Verma, D. Tyagi K, et al., “FedHC: Enhanced federated learning with Hessian and cosine correlation for proximal correlation,” Knowledge-Based Systems, vol. 341, Art. no. 115775, 2026, doi: 10.1016/j.knosys.2026.115775.
L. Su, J. Guo, J. Liu, et al., “Fair client selection for multi-task federated learning in mobile edge networks,” Information Processing and Management, vol. 63, no. 6, Art. no. 104748, 2026, doi: 10.1016/j.ipm.2026.104748.
S. An, K. Zhang, Y. Su, et al., “Privacy-preserving medical decision-making and service differentiation in a federated learning framework,” Omega, vol. 143, Art. no. 103561, 2026, doi: 10.1016/j.omega.2026.103561.
A. Yang, S. Luo, K. Zhu, et al., “Hierarchical privacy-preserving federated recommendation via adaptive multi-level personalization and dynamic aggregation,” Physica A: Statistical Mechanics and its Applications, vol. 690, Art. no. 131464, 2026, doi: 10.1016/j.physa.2026.131464.
H. Huang, Q. Zhou, Y. Hao, et al., “AFCG: A privacy-preserving federated learning framework against chained malicious attacks for vehicular networks,” Ad Hoc Networks, vol. 187, Art. no. 104225, 2026, doi: 10.1016/j.adhoc.2026.104225.
Y. He, W. Wang, X. Chen, et al., “Federated learning enhanced spatial and temporal attention mechanism for multivariate time series anomaly detection,” Applied Soft Computing, vol. 196, Art. no. 115048, 2026, doi: 10.1016/j.asoc.2026.115048.
Z. Zhang, R. Li, K. Guo, et al., “Personalized federated learning with personalized knowledge distillation based on local empirical risk,” Information Fusion, vol. 133, Art. no. 104269, 2026, doi: 10.1016/j.inffus.2026.104269.
N. Naveenkumar, T. Subarna, S. Pragadeeswaran, et al., “Federated learning based hybrid DL-based transformer model for heart disease detection with Explainable AI,” Biomedical Signal Processing and Control, vol. 120, no. PB, Art. no. 110076, 2026, doi: 10.1016/j.bspc.2026.110076.
E. Akpinar, M. Taskiran, and B. Bolat, “PARS: Performance-driven adam-based resilient scaffold for federated learning,” Information Sciences, vol. 744, Art. no. 123374, 2026, doi: 10.1016/j.ins.2026.123374.
W. Algethami, G. Wu, F. Alshami, et al., “Entropy-guided meta-learning defense against data poisoning attacks in blockchain-assisted federated learning,” Information Sciences, vol. 745, Art. no. 123389, 2026, doi: 10.1016/j.ins.2026.123389.
W. Li, A. Halimi, J. Vaidya, et al., “Privacy-preserving verification of preprocessing in federated learning for genomic data,” JAMIA Open, pp. 9(2), 2026, doi: 10.1093/jamiaopen/ooag040.
A. Beznosikov, G. Kormakov, A. Grigorievskiy, et al., “Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation,” Journal of Optimization Theory and Applications, vol. 209, no. 1, pp. 18, 2026, doi: 10.1007/s10957-026-02961-z.