Double Confidential Federated Machine Learning Logistic Regression for Industrial Data Platforms

Research paper on Double Confidential Federated Learning published at International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020 (FL-ICML'20). The training data confidentiality is preserved, as in any Federated Learning scheme, and the model confidentiality is also preserved, since it is only known by the aggregator, not shared with the other participants.