[NOTE] Please note that this repository does not contain the blockchain smart contracts which were left in my previous lab and I do not have access to the system, please feel free to clone the repository, make changes, and push them back to help other researchers in the area.
This repository presents a blockchain-based framework, TrustFed, for Cross-Device Federated Learning systems to detect the model poisoning attacks, enable fair training settings, and maintain the participating devices' reputation. TrustFed provides fairness by detecting and removing the attackers from the training distributions. It uses blockchain smart contracts to maintain participating devices' reputations to compel the participants in bringing active and honest model contributions. We implemented the TrustFed using a python-simulated FL framework, blockchain smart contracts, and statistical outlier detection techniques.
Muhammad Habib ur Rehman, Ahmed Mukhtar Dirir, Khaled Salah, Ernesto Damiani, Davor Svetinovic, "TrustFed: A Framework for Fair and Trustworthy Cross-Device Federated Learning in IIoT", IEEE Transactions on Industrial Informatics, April 2021.