Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jia, Wenyang, Xu, Qiankang, Yan, Ziwei, Kang, Chunhua, Yang, Yang, He, Jinglu, Lei, Kai
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.04091
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917462437527552
author Jia, Wenyang
Xu, Qiankang
Yan, Ziwei
Kang, Chunhua
Yang, Yang
He, Jinglu
Lei, Kai
author_facet Jia, Wenyang
Xu, Qiankang
Yan, Ziwei
Kang, Chunhua
Yang, Yang
He, Jinglu
Lei, Kai
contents Decentralized Federated Learning (DFL) eliminates the central aggregator but introduces a severe 'trust gap': without a trusted coordinator, the system becomes vulnerable to Byzantine and Sybil attacks, while existing solutions treat node selection, aggregation, and consensus as isolated modules, often relying on a trusted root dataset unavailable in truly decentralized settings.We propose OpenCLAW-Nexus, a self-reinforcing trust framework that bridges this gap through a single primitive, a discounted Beta-reputation model, that unifies reputation-based node selection, reputation-weighted aggregation Rep-FedAvg, and reputation-aware BFT consensus. Rep-FedAvg eliminates the trusted root dataset requirement; we formally prove reputation separation between honest and Byzantine nodes under non-IID data with noisy evaluations.On a 1,000-node global testbed spanning three cloud providers and nine regions, Rep-FedAvg achieves 72.6% accuracy on non-IID CIFAR-10 with 20% Byzantine nodes and record-level differential privacy, within 0.5,pp of centralized FLTrust.Under a 300-node Sybil attack, reputation-weighted consensus maintains 84.2% validation correctness versus 62.8% (PoW) and 47.6% (PoS).
format Preprint
id arxiv_https___arxiv_org_abs_2605_04091
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OpenCLAW-Nexus: A Self-Reinforcing Trust Framework for Byzantine-Resilient Decentralized Federated Learning
Jia, Wenyang
Xu, Qiankang
Yan, Ziwei
Kang, Chunhua
Yang, Yang
He, Jinglu
Lei, Kai
Networking and Internet Architecture
Decentralized Federated Learning (DFL) eliminates the central aggregator but introduces a severe 'trust gap': without a trusted coordinator, the system becomes vulnerable to Byzantine and Sybil attacks, while existing solutions treat node selection, aggregation, and consensus as isolated modules, often relying on a trusted root dataset unavailable in truly decentralized settings.We propose OpenCLAW-Nexus, a self-reinforcing trust framework that bridges this gap through a single primitive, a discounted Beta-reputation model, that unifies reputation-based node selection, reputation-weighted aggregation Rep-FedAvg, and reputation-aware BFT consensus. Rep-FedAvg eliminates the trusted root dataset requirement; we formally prove reputation separation between honest and Byzantine nodes under non-IID data with noisy evaluations.On a 1,000-node global testbed spanning three cloud providers and nine regions, Rep-FedAvg achieves 72.6% accuracy on non-IID CIFAR-10 with 20% Byzantine nodes and record-level differential privacy, within 0.5,pp of centralized FLTrust.Under a 300-node Sybil attack, reputation-weighted consensus maintains 84.2% validation correctness versus 62.8% (PoW) and 47.6% (PoS).
title OpenCLAW-Nexus: A Self-Reinforcing Trust Framework for Byzantine-Resilient Decentralized Federated Learning
topic Networking and Internet Architecture
url https://arxiv.org/abs/2605.04091