Privacy-Preserving Federated Learning for Personalized Healthcare Diagnostics on Mobile Devices with a Secure JSP-Based Model Aggregation Portal

A privacy-preserving federated learning system for personalised healthcare diagnostics on mobile devices, with a secure JSP-based model aggregation portal.

A privacy-preserving federated learning system for personalised healthcare diagnostics on mobile devices, with a secure JSP-based model aggregation portal. As a reference project it shows how a system like this is put together in practice, which parts matter and how they are tested, so that a developer can learn from it and build on it.

It suits learners building full-stack skills: user accounts and roles, a database-backed back end, a responsive front end and deployment.

The main parts are privacy-preserving training across several clients, with only model updates shared, security and privacy controls such as encryption and access control, secure sign-up with role-based access, a database-backed back end with a clear API, and a responsive interface for each type of user. The reference build uses Flower, React, Node.js, Express, and PostgreSQL, with a clear project structure, setup instructions and sample data so that it can be run and extended.