aiqbench analysis
This research introduces a federated learning framework that combines dynamic differential privacy, lightweight homomorphic encryption, and asynchronous aggregation to secure distributed model training. The approach successfully maintains high classification accuracy on standard benchmarks while significantly reducing communication overhead in environments with strict privacy constraints. It offers a practical technical foundation for scaling collaborative machine learning without compromising data confidentiality or performance.
Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation
arXiv:2609.15885v1 Announce Type: cross 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 ({\epsilon} = 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.
Authors:Zhen Zhong (1), Shini Yang (2), Liesheng Wei (3) ((1) Georgetown University, Washington, D.C., USA, (2) LinkedIn, CA, USA, (3) Shanghai Ocean University, Shanghai, China)
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 ({\epsilon} = 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.
Published in Proc. SPIE 14128, Third International Conference on Big Data, Computational Intelligence, and Applications (BDCIA 2025), 141283L. Event: BDCIA 2025, Huanggang, China. this https URL
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Databases (cs.DB)
arXiv:2609.15885 [cs.LG]
(or arXiv:2609.15885v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.15885 arXiv-issued DOI via DataCite (pending registration)
Proc. SPIE 14128, Third International Conference on Big Data, Computational Intelligence, and Applications (BDCIA 2025), 141283L (2026)
https://doi.org/10.1117/12.3106592 DOI(s) linking to related resources
Full text under the publisher's open licence · 228 words
Related coverage
AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments
arXiv · Jun 9, 2026
Federated Learning Without the Refactoring Overhead Using NVIDIA FLARE
NVIDIA · Apr 24, 2026
Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station
arXiv · Oct 5, 2026
Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation
arXiv · Jun 9, 2026