HARPOCRATES: Federated Data Analysis for Social Utility

Project Summary

The project leverages novel cryptographic schemes to advance the capabilities of Privacy Preserving Machine Learning (PPML) and Federated Learning (FL), thus enabling decentralised training, validation, and prediction on encrypted data.

It focuses on setting the foundations of digitally blind evaluation systems that will, by design, eliminate proxies such as geography, gender, race, and others and eventually have a tangible impact on building fairer, democratic and unbiased societies.

The Partners

Research is being conducted in collaboration with the following organizations:

🇫🇮 Tampere University (Finland) – Coordinator
🇸🇪 RI.SE (Sweden)
🇮🇪 Trilateral Research (Ireland)
🇷🇸 Zentrix Lab (Serbia)
🇩🇪 Universitaetsmedizin Berlin (Germany)
🇩🇪 Universitaetsmedizin Göttingen (Germany)
🇪🇸 Sociedad Aragonesa de Gestión Agroambiental – SARGA (Spain)
🇮🇹 Regione Veneto (Italy)
🇫🇮 University of Eastern Finland (Finland)
🇫🇷 Université Paris Cité (France)
🇪🇸 S2 GRUPO (Spain)
🇬🇧 University of Westminster (United Kingdom)