Description du projet
Améliorer la confidentialité des données dans l’apprentissage fédéré grâce à de nouvelles méthodes
Le projet TRUMPET, financé par l’UE, mènera des recherches afin de remédier aux vulnérabilités en matière de confidentialité de l’apprentissage fédéré en les identifiant et en mettant au point de nouvelles technologies de renforcement de la confidentialité qui contribueront à les atténuer. Le projet vise également à créer une plateforme de services d’IA fédérée évolutive qui renforcera la confidentialité globale des données et permettra aux chercheurs de réaliser des études alimentées par l’IA sur des ensembles de données européennes en bénéficiant d’un niveau de confidentialité accru. Afin de démontrer la sécurité de cette nouvelle méthode, le projet fera appel à des experts et à des organisations tierces pour tester et améliorer la plateforme dans deux cas d’utilisation de l’apprentissage fédéré dans le domaine de la santé en ligne.
Objectif
In recent years, Federated Learning (FL) has emerged as a revolutionary privacy-enhancing technology and, consequently, has quickly expanded to other applications.
However, further research has cast a shadow of doubt on the strength of privacy protection provided by FL. Potential vulnerabilities and threats pointed out by researchers included a curious aggregator threat; susceptibility to man-in-the-middle and insider attacks that disrupt the convergence of global and local models or cause convergence to fake minima; and, most importantly, inference attacks that aim to re-identify data subjects from FL’s AI model parameter updates.
The goal of TRUMPET is to research and develop novel privacy enhancement methods for Federated Learning, and to deliver a highly scalable Federated AI service platform for researchers, that will enable AI-powered studies of siloed, multi-site, cross-domain, cross border European datasets with privacy guarantees that exceed the requirements of GDPR. The generic TRUMPET platform will be piloted, demonstrated and validated in the specific use case of European cancer hospitals, allowing researchers and policymakers to extract AI-driven insights from previously inaccessible cross-border, cross-organization cancer data, while ensuring the patients’ privacy. The strong privacy protection accorded by the platform will be verified through the engagement of external experts for independent privacy leakage and re-identification testing.
A secondary goal is to research, develop and promote with EU data protection authorities a novel metric and tool for the certification of GDPR compliance of FL implementations.
The consortium is composed of 9 interdisciplinary partners: 3 Research Organizations, 1 University, 3 SMEs and 2 Clinical partners with extensive experience and expertise to guarantee the correct performance of the activities and the achievement of the results.
Champ scientifique
Mots‑clés
Programme(s)
Régime de financement
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinateur
36214 VIGO
Espagne