Decentralized Federated Learning Framework with Blockchain-based Incentive and Reputation Mechanism

Abstract

Federated Learning (FL) enables collaborative model training while preserving data privacy but relies on centralized aggregation servers, leading to issues such as lack of transparency, vulnerability to malicious updates, and single points of failure. This paper proposes a decentralized federated learning framework integrating blockchain technology and the InterPlanetary File System (IPFS) to eliminate central authority and enhance trust. Smart contracts deployed on the Ethereum Sepolia testnet manage model submission, validation, incentive distribution, and reputation tracking. Model updates are stored off-chain using IPFS, while their hashes are recorded on the blockchain to ensure integrity and immutability. A staking and slashing mechanism is introduced to encourage honest participation, where valid contributions are rewarded and malicious updates are penalized. A reputation system further evaluates participant reliability over time. The system is implemented using PyTorch, Solidity, Web3.py, and React.js. Experimental results demonstrate improved security, transparency, and efficient decentralized coordination, highlighting the feasibility of integrating federated learning with blockchain and decentralized storage for scalable and trustworthy machine learning applications.