Toward Trustworthy AI: Blockchain-Based Architecture Design for Accountability and Fairness of Federated Learning Systems

Federated learning is an emerging privacy-preserving AI technique where clients (i.e., organizations or devices) train models locally and formulate a global model based on the local model updates without transferring local data externally. However, federated learning systems struggle to achieve trustworthiness and embody responsible AI principles. In particular, federated learning systems face accountability and fairness challenges due to multistakeholder involvement and heterogeneity in client data distribution. To enhance the accountability and fairness of federated learning systems, we present a blockchain-based trustworthy federated learning architecture. We first design a smart contract-based data-model provenance registry to enable accountability. Additionally, we propose a weighted fair data sampler algorithm to enhance fairness in training data. We evaluate the proposed approach using a COVID-19 X-ray detection use case. The evaluation results show that the approach is feasible to enable accountability and improve fairness. The proposed algorithm can achieve better performance than the default federated learning setting in terms of the model's generalization and accuracy.

Automated summary

Federated learning is a privacy-preserving AI technique that involves training models locally and aggregating them without transferring data externally. However, accountability and fairness are major challenges in federated learning systems due to stakeholder involvement and data distribution heterogeneity. To address these challenges, a blockchain-based architecture is proposed, incorporating a smart contract-based registry for accountability and a fair data sampler algorithm. Evaluation using a COVID-19 X-ray detection use case demonstrates the feasibility of this approach, with improved model performance compared to default federated learning settings.