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

arXiv: https://arxiv.org/abs/2502.06917 · HTML: https://mlsanity.com/paper/2502.06917/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- First posted on arXiv 10 Feb 2025.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Built on by (most cited first, 3 of 3)

- [Secure and Private Federated Learning: Achieving Adversarial Resilience through Robust Aggregation](https://mlsanity.com/paper/2505.17226/) (2025)
- [Byzantine Machine Learning: MultiKrum and an optimal notion of robustness](https://mlsanity.com/paper/2602.03899/) (2026)
- [Byzantine Accountability Without Consensus: Strong Eventual Consistency for Non-Associative, Stochastic, Robust Aggregation](https://mlsanity.com/paper/2607.10305/) (2026)

## Abstract (arXiv)

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.