Federated Learning Techniques for Privacy-Preserving Distributed Model Training

Johanna Schwarz

Federated Learning Techniques for Privacy-Preserving Distributed Model Training

Authors

Johanna Schwarz

Federated Learning Researcher, Germany.

Keywords:

Federated Learning, Privacy Preservation, Distributed Training, Differential Privacy, Secure Aggregation, Data Decentralization

Synopsis

The increasing reliance on machine learning models across sectors such as healthcare, finance, and smart infrastructure has raised critical concerns regarding data privacy and security. Traditional centralized training paradigms require data to be aggregated in a single repository, creating vulnerabilities to breaches and regulatory challenges. Federated Learning (FL) has emerged as a promising solution to enable collaborative model training without transferring raw data. This paper explores the evolution of federated learning techniques, focusing on their capacity to preserve privacy while achieving competitive model performance across distributed data environments. It surveys advancements, evaluates key technical strategies, presents comparative metrics in privacy-preserving efficacy, and outlines future challenges and opportunities in practical deployments.

References

[1] Abadi, Martin, et al. Deep Learning with Differential Privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS), ACM, 2016, pp. 308–318.

[2] Arivazhagan, Moustafa, et al. Federated Learning with Personalization Layers. arXiv preprint arXiv:1912.00818, 2019.

[3] Bonawitz, Keith, et al. Practical Secure Aggregation for Privacy-Preserving Machine Learning. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS), ACM, 2017, pp. 1175–1191.

[4] Geyer, Robin C., Tassilo Klein, and Moin Nabi. Differentially Private Federated Learning: A Client Level Perspective. Workshop on Private Multi-Party Machine Learning, Advances in Neural Information Processing Systems (NeurIPS), 2017.

[5] Kairouz, Peter, et al. Advances and Open Problems in Federated Learning. arXiv preprint arXiv:1912.04977, 2019.

[6] Li, Qiang, Bingshuai He, and Dawn Song. Model-Contrastive Federated Learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2021, pp. 10713–10722.

[7] Sirimalla A. Autonomous Performance Tuning Framework for Databases Using Python and Machine Learning. J Artif Intell Mach Learn & Data Sci 2023 1(4), 3139-3147. DOI: doi.org/10.51219/JAIMLD/adithya-sirimalla/642

[8] McMahan, H. Brendan, et al. Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, 2017, pp. 1273–1282.

[9] Papernot, Nicolas, et al. Scalable Private Learning with PATE. International Conference on Learning Representations (ICLR), 2018.

[10] Shokri, Reza, and Vitaly Shmatikov. Privacy-Preserving Deep Learning. Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security (CCS), ACM, 2015, pp. 1310–1321.

[11] Truex, Stacey, et al. A Hybrid Approach to Privacy-Preserving Federated Learning. Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security (AISec), ACM, 2019, pp. 1–11.

[12] Sirimalla, A. (2022). End-to-end automation for cross-database DevOps deployments: CI/CD pipelines, schema drift detection, and performance regression testing in the cloud. World Journal of Advanced Research and Reviews, 14(3), 871–889. https://doi.org/10.30574/wjarr.2022.14.3.0555

[13] Smith, Virginia, et al. Federated Multi-Task Learning. Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.

[14] Zhao, Yue, et al. Federated Learning with Non-IID Data. arXiv preprint arXiv:1806.00582, 2018.