# FLoW3 -- Web3 Empowered Federated Learning

arXiv: https://arxiv.org/abs/2312.05459 · HTML: https://mlsanity.com/paper/2312.05459/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 16 of its 53 references that are in the map.
- First posted on arXiv 9 Dec 2023.

## Placed in

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

## Builds on (most cited first, 16 of 16)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [Blockchained On-Device Federated Learning](https://mlsanity.com/paper/1808.03949/) (2018)
- [A Blockchain-based Decentralized Federated Learning Framework with Committee Consensus](https://mlsanity.com/paper/2004.00773/) (2020)
- [Federated Learning: Opportunities and Challenges](https://mlsanity.com/paper/2101.05428/) (2021)
- [Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challenges](https://mlsanity.com/paper/2104.01776/) (2021)
- [IPFS - Content Addressed, Versioned, P2P File System](https://mlsanity.com/paper/1407.3561/) (2014)
- [A Framework for Evaluating Gradient Leakage Attacks in Federated Learning](https://mlsanity.com/paper/2004.10397/) (2020)
- [Blockchain Technology Overview](https://mlsanity.com/paper/1906.11078/) (2019)
- [Web3: The Next Internet Revolution](https://mlsanity.com/paper/2304.06111/) (2023)
- [Scalable and Probabilistic Leaderless BFT Consensus through Metastability](https://mlsanity.com/paper/1906.08936/) (2019)
- [Trustworthy Privacy-preserving Hierarchical Ensemble and Federated Learning in Healthcare 4.0 with Blockchain](https://mlsanity.com/paper/2305.09209/) (2023)
- [Towards Web3 Applications: Easing the Access and Transition](https://mlsanity.com/paper/2210.05903/) (2022)

## Abstract (arXiv)

Federated Learning is susceptible to various kinds of attacks like Data Poisoning, Model Poisoning and Man in the Middle attack. We perceive Federated Learning as a hierarchical structure, a federation of nodes with validators as the head. The process of validation is done through consensus by employing Novelty Detection and Snowball protocol, to identify valuable and relevant updates while filtering out potentially malicious or irrelevant updates, thus preventing Model Poisoning attacks. The opinion of the validators is recorded in blockchain and trust score is calculated. In case of lack of consensus, trust score is used to determine the impact of validators on the global model. A hyperparameter is introduced to guide the model generation process, either to rely on consensus or on trust score. This approach ensures transparency and reliability in the aggregation process and allows the global model to benefit from insights of most trusted nodes. In the training phase, the combination of IPFS , PGP encryption provides : a) secure and decentralized storage b) mitigates single point of failure making this system reliable and c) resilient against man in the middle attack. The system is realized by implementing in python and Foundry for smart contract development. Global Model is tested against data poisoning by flipping the labels and by introducing malicious nodes. Results found to be similar to that of Flower.