PRA-DFL: privacy-preserving ring-based aggregation for decentralized federated learning
The Computer Journal · 29.06.2026
DOI: 10.1093/comjnl/bxag070 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Computer Journal, online erschienen am 29.06.2026. Verfasst von Runze Wu und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Gefördert von: Youth Innovation Team of Shaanxi Universities.
Abstract (Originalsprache)
The rapid growth of distributed data has intensified the problem of “data silos,” motivating federated learning (FL) as a privacy-preserving paradigm for collaborative model training. Decentralized FL (DFL) further eliminates reliance on a central server, improving scalability and robustness. However, existing DFL schemes still face serious challenges in security and efficiency. Many privacy-preserving solutions rely on costly homomorphic encryption, assume semi-honest adversaries, or incur high communication overhead without effectively identifying malicious participants. In this paper, we propose PRA-DFL, a privacy-preserving ring-based aggregation framework for DFL that achieves strong security guarantees with low overhead. PRA-DFL organizes participants into a ring topology, where each node and its two neighbors form a three-party computation system based on replicated secret sharing. This structure enables secure model aggregation while maintaining constant per-node communication complexity, independent of network size. Moreover, PRA-DFL is resilient to both semi-honest and malicious adversaries. By incorporating the SPDZ-style secret sharing, the framework supports malicious node identification in the reconstruction phase. We evaluate PRA-DFL on four datasets. Experimental results show that PRA-DFL achieves accuracy comparable to that of existing centralized and decentralized FL approaches, while incurring low computational and communication overhead, making it suitable for resource-constrained decentralized learning environments.
Förderung
- Youth Innovation Team of Shaanxi Universities
Zitieren
APA
Wu, R., & Wang, B. (2026). PRA-DFL: privacy-preserving ring-based aggregation for decentralized federated learning. The Computer Journal. https://doi.org/10.1093/comjnl/bxag070
Vancouver
Wu R, Wang B. PRA-DFL: privacy-preserving ring-based aggregation for decentralized federated learning. The Computer Journal. 2026. doi:10.1093/comjnl/bxag070
BibTeX
@article{Wu2026,
author = {Wu, Runze and Wang, Baocang},
title = {PRA-DFL: privacy-preserving ring-based aggregation for decentralized federated learning},
journal = {The Computer Journal},
year = {2026},
doi = {10.1093/comjnl/bxag070}
}
EUVIMED