FLORA

FLORA is an innovative health application focusing on ovulation tracking while prioritizing user privacy and data security. Utilizing advanced technologies such as federated learning and blockchain, FLORA ensures user data remains private and secure on their devices. The project aligns with TRUSTCHAIN objectives and leverages cutting-edge machine learning and cryptographic techniques to enhance user experience and data protection.

Motivation for the project: FLORA addresses the significant privacy concerns prevalent in health applications. Ovulation Tracker apps have become indispensable tools for women. However, recent studies show that many period trackers lack privacy safeguards and share data without user consent, this putting user rights at risk.
Generic use case description: FLORA provides an ovulation tracking solution that prioritizes user privacy and data security. Users can track their health metrics through a user-friendly mobile application. Federated Learning, PETs and Blockchain are used to minimize data beaches.
Essential functionalities: A user-friendly health app leveraging Federated Learning PETs: Fully Homomorphic Encryption, Differential Privacy, and Proxy Re-Encryption Digital Identity; Management/Consent System: Manages identities and consent Model Market and Reward System: Users share anonymized data models and receive rewards
How these functionalities can be integrated within the software ecosystem: The project follows a microservices approach, where each of the suggested functionalities will be implemented using a submodule. This design strategy allows for greater flexibility, as each submodule can be developed and deployed independently. By modularizing functionalities, the project ensures interoperability.
Gap being addressed: FLORA addresses critical gaps in health tracking applications by significantly enhancing user privacy. Traditional apps often store sensitive health data on centralized servers, making them vulnerable to unauthorized access. FLORA overcomes this in a decentralized approach that aligns with GDPR.
Expected benefits achieved with the novel technology building blocks:
Enhanced Privacy: Protects user data through advanced encryption and federated learning
User Empowerment: Gives users control over their data
Accurate Ovulation Tracking: Provides reliable health metrics by leveraging ML
Ethical AI Usage: Demonstrates responsible AI deployment in health applications
Potential demonstration scenario: FLORA will be piloted with real end-users to gather feedback and validate its functionalities, ensuring it meets user needs and regulatory requirements.