ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learning

TL;DR

ZK-HybridFL is a decentralized federated learning framework that uses zero-knowledge proofs and a DAG ledger to ensure privacy, security, and efficiency in model validation and update verification.

Contribution

It introduces a novel integration of zero-knowledge proofs with a DAG-based ledger and sidechains for secure, scalable, and privacy-preserving federated learning.

Findings

Faster convergence and higher accuracy in image and language tasks.

Robust against adversarial and idle nodes, ensuring security.

Supports sub-second on-chain verification with low gas usage.

Abstract

Federated learning (FL) enables collaborative model training while preserving data privacy, yet both centralized and decentralized approaches face challenges in scalability, security, and update validation. We propose ZK-HybridFL, a secure decentralized FL framework that integrates a directed acyclic graph (DAG) ledger with dedicated sidechains and zero-knowledge proofs (ZKPs) for privacy-preserving model validation. The framework uses event-driven smart contracts and an oracle-assisted sidechain to verify local model updates without exposing sensitive data. A built-in challenge mechanism efficiently detects adversarial behavior. In experiments on image classification and language modeling tasks, ZK-HybridFL achieves faster convergence, higher accuracy, lower perplexity, and reduced latency compared to Blade-FL and ChainFL. It remains robust against substantial fractions of adversarial and idle nodes, supports sub-second on-chain verification with efficient gas usage, and prevents invalid updates and orphanage-style attacks. This makes ZK-HybridFL a scalable and secure solution for decentralized FL across diverse environments.