OpenCLAW-Nexus: A Self-Reinforcing Trust Framework for Byzantine-Resilient Decentralized Federated Learning
For decentralized federated learning systems, this framework provides a practical solution to Byzantine and Sybil attacks without requiring a trusted root dataset.
OpenCLAW-Nexus addresses the trust gap in decentralized federated learning by unifying reputation-based node selection, aggregation, and consensus into a single framework. It achieves 72.6% accuracy on non-IID CIFAR-10 with 20% Byzantine nodes and 84.2% validation correctness under Sybil attacks, outperforming PoW and PoS.
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).