Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

End-to-End Verifiable Decentralized Federated Learning

Chaehyeon Lee, Jonathan Heiss, Stefan Tai, James Won-Ki Hong

TL;DR

This work addresses the lack of end-to-end integrity in decentralized federated learning by introducing a two-step proving and verification (2PV) framework that adds non-disclosing authenticity proofs for data sources and certificates of devices. It integrates on-chain verification of aggregates with off-chain zkSNARK-based learning while protecting confidential inputs, enabling end-to-end verifiability from certified edge devices to blockchain storage. The key contributions include the system model with three layers, the 2PV registration and learning workflows, and a ZoKrates-based prototyping implementation demonstrating feasible overheads. The approach enhances resilience against data poisoning and Sybil attacks in IoT/healthcare scenarios, with practical implications for secure, auditable collaborative learning at scale.

Abstract

Verifiable decentralized federated learning (FL) systems combining blockchains and zero-knowledge proofs (ZKP) make the computational integrity of local learning and global aggregation verifiable across workers. However, they are not end-to-end: data can still be corrupted prior to the learning. In this paper, we propose a verifiable decentralized FL system for end-to-end integrity and authenticity of data and computation extending verifiability to the data source. Addressing an inherent conflict of confidentiality and transparency, we introduce a two-step proving and verification (2PV) method that we apply to central system procedures: a registration workflow that enables non-disclosing verification of device certificates and a learning workflow that extends existing blockchain and ZKP-based FL systems through non-disclosing data authenticity proofs. Our evaluation on a prototypical implementation demonstrates the technical feasibility with only marginal overheads to state-of-the-art solutions.

End-to-End Verifiable Decentralized Federated Learning

TL;DR

This work addresses the lack of end-to-end integrity in decentralized federated learning by introducing a two-step proving and verification (2PV) framework that adds non-disclosing authenticity proofs for data sources and certificates of devices. It integrates on-chain verification of aggregates with off-chain zkSNARK-based learning while protecting confidential inputs, enabling end-to-end verifiability from certified edge devices to blockchain storage. The key contributions include the system model with three layers, the 2PV registration and learning workflows, and a ZoKrates-based prototyping implementation demonstrating feasible overheads. The approach enhances resilience against data poisoning and Sybil attacks in IoT/healthcare scenarios, with practical implications for secure, auditable collaborative learning at scale.

Abstract

Verifiable decentralized federated learning (FL) systems combining blockchains and zero-knowledge proofs (ZKP) make the computational integrity of local learning and global aggregation verifiable across workers. However, they are not end-to-end: data can still be corrupted prior to the learning. In this paper, we propose a verifiable decentralized FL system for end-to-end integrity and authenticity of data and computation extending verifiability to the data source. Addressing an inherent conflict of confidentiality and transparency, we introduce a two-step proving and verification (2PV) method that we apply to central system procedures: a registration workflow that enables non-disclosing verification of device certificates and a learning workflow that extends existing blockchain and ZKP-based FL systems through non-disclosing data authenticity proofs. Our evaluation on a prototypical implementation demonstrates the technical feasibility with only marginal overheads to state-of-the-art solutions.
Paper Structure (31 sections, 5 figures, 1 table)

This paper contains 31 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background
  3. Federated Learning
  4. ZkSNARKs and ZoKrates
  5. Related Work
  6. Model
  7. Motivating Scenario and Verifiability Objectives
  8. System Overview
  9. Aggregation Layer
  10. Learning Layer
  11. Data Layer
  12. Problem Statement
  13. System Design
  14. System Initialization
  15. One-Time Registration Workflow
  16. ...and 16 more sections

Figures (5)

  • Figure 1: Federated Learning Overview
  • Figure 2: Overall System Architecture
  • Figure 3: One-time Registration Workflow for Non-disclosing Device Certificate Verification.
  • Figure 4: Iterative Learning Workflow for Non-disclosing Verification of Model Integrity and Data Authenticity.
  • Figure 5: Accuracy for various batch sizes