Krum Federated Chain (KFC): Using blockchain to defend against adversarial attacks in Federated Learning

2025-02-10

AI Summary

To address the lack of robustness against Byzantine and backdoor attacks in federated learning (FL), this paper proposes Krum Federated Chain (KFC)—the first decentralized, secure FL training framework integrating blockchain with robust aggregation. The method introduces a novel Proof of Federated Learning (PoFL) consensus mechanism, rigorously proven to block all malicious model updates even when only a single honest node remains. Crucially, the Krum robust aggregation algorithm is deeply embedded into the blockchain’s consensus layer, enabling unconditional coupling between Krum selection and block validation—ensuring model convergence and security even under total miner compromise. Evaluated on image classification tasks, KFC achieves >92% accuracy, significantly outperforming existing baselines. By eliminating reliance on trusted third parties, KFC establishes a verifiable, tamper-resistant, and robust collaborative training paradigm for FL.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Safety and Robustness
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Blockchains and distributed ledgers
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Federated Learning presents a nascent approach to machine learning, enabling collaborative model training across decentralized devices while safeguarding data privacy. However, its distributed nature renders it susceptible to adversarial attacks. Integrating blockchain technology with Federated Learning offers a promising avenue to enhance security and integrity. In this paper, we tackle the potential of blockchain in defending Federated Learning against adversarial attacks. First, we test Proof of Federated Learning, a well known consensus mechanism designed ad-hoc to federated contexts, as a defense mechanism demonstrating its efficacy against Byzantine and backdoor attacks when at least one miner remains uncompromised. Second, we propose Krum Federated Chain, a novel defense strategy combining Krum and Proof of Federated Learning, valid to defend against any configuration of Byzantine or backdoor attacks, even when all miners are compromised. Our experiments conducted on image classification datasets validate the effectiveness of our proposed approaches.

Problem

• Defend Federated Learning against adversarial attacks.
• Integrate blockchain for enhanced security.
• Propose Krum Federated Chain strategy.

Innovation

• Blockchain enhances Federated Learning security
• Krum Federated Chain defends against attacks
• Proof of Federated Learning ensures integrity