Described as the "fuel of the digital era", personal and private data is the fuel of all desires. Collected, analyzed and exploited, users’ data offer unprecedented opportunities for innovation, but raise real concerns about data privacy. The emergence of AI enabled-applications accentuates data privacy issues.

Federated learning is a promising on-device machine learning scheme and new research topic on privacy-preserving machine learning. Federated learning becomes a paradigm shift in privacy-preserving AI and offers an attractive framework for training large-scale distributed learning models on sensitive data. However, federated learning still faces many challenges to fully preserve data privacy.

This project tackles the cybersecurity challenges of federated learning systems in terms of data privacy. To achieve this goal, we will extend different federated learning approaches to consider their limitations in terms of accuracy, confidentiality, robustness, explainability and fairness.

trusty-ia.citi-lab.fr