Reputation-Driven Federated Learning: Enhancing Trust in Healthcare Data Sharing with Blockchain
Abstract
Abstract Sharing healthcare data poses severe threats to the privacy of patients, who from one side can take benefit from advanced techniques for disease diagnosis, but on the other side can suffer from malicious deployment of the shared information. Distributed ledger technologies in combination with federated learning can provide innovative data-sharing mechanisms that give guarantees for the trustworthiness of collected data and for the privacy of the patients. In this paper we present a novel and reliable access control method for sharing healthcare-based Federated Learning (FL) models built on blockchain technology. This work presents a distributed FL-based model sharing architecture to ensure privacy and security of healthcare data by employing an Attribute-based Access Control (ABAC) model, where the trust attribute is calculated and used in the ABAC model for access control decision. Furthermore, it provides a trust monitoring method for remote healthcare model sharing to detect malicious nodes in the FL network.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.