Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation

arXiv:2609.15885 · cs.LG, cs.AI, cs.CE, cs.DB · Submitted 2026-09-14 · Read on arXiv

cs.LG, cs.AI, cs.CE, cs.DB

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: Published in Proc. SPIE 14128, Third International Conference on Big Data, Computational Intelligence, and Applications (BDCIA 2025), 141283L. Event: BDCIA 2025, Huanggang, China. https://doi.org/10.1117/12.3106592

Journal ref: Proc. SPIE 14128, Third International Conference on Big Data, Computational Intelligence, and Applications (BDCIA 2025), 141283L (2026)

DOI: 10.1117/12.3106592

License: http://creativecommons.org/licenses/by/4.0/

The gist: This study proposes a privacy-enhanced federated learning framework to address secure collaborative training in distributed data environments.

Terminology

Abstract

This study proposes a privacy-enhanced federated learning framework to address secure collaborative training in distributed data environments. The framework integrates Dynamic Differential Privacy (DDP), lightweight Homomorphic Encryption (HE), and Local Differential Privacy (LDP) mechanisms to ensure data privacy protection during model training. Additionally, the framework employs an asynchronous aggregation strategy with version control to support distributed training in asynchronous environments. Experimental validation on the CIFAR-10 and Purchase-100 benchmark datasets demonstrates that the method maintains high classification accuracy (up to 82.6%) even under stringent privacy constraints (ε = 0.1), while reducing communication overhead by 21.3% compared to FedAvg. Experimental results demonstrate that this framework effectively balances privacy protection and model performance in distributed machine learning scenarios, providing a scalable technical foundation for large-scale distributed collaborative computing.

Sources

Related papers