RT Journal Article
SR Electronic
T1 Privacy-Preserving Federated Neural Network Learning for Disease-Associated Cell Classification
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2022.01.10.475610
DO 10.1101/2022.01.10.475610
A1 Sinem Sav
A1 Jean-Philippe Bossuat
A1 Juan R. Troncoso-Pastoriza
A1 Manfred Claassen
A1 Jean-Pierre Hubaux
YR 2022
UL http://biorxiv.org/content/early/2022/01/11/2022.01.10.475610.abstract
AB Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data-silos. Sharing or centralizing the data of different healthcare institutions is, however, unfeasible or prohibitively difficult due to privacy regulations. In this work, we address this problem by using a novel privacy-preserving federated learning-based approach, PriCell, for complex machine learning models such as convolutional neural networks. PriCell relies on multiparty homomorphic encryption and enables the collaborative training of encrypted neural networks with multiple healthcare institutions. We preserve the confidentiality of each institutions’ input data, of any intermediate values, and of the trained model parameters. We efficiently replicate the training of a published state-of-the-art convolutional neural network architecture in a decentralized and privacy-preserving manner. Our solution achieves an accuracy comparable to the one obtained with the centralized solution, with an improvement of at least one-order-of-magnitude in execution time with respect to prior secure solutions. Our work guarantees patient privacy and ensures data utility for efficient multi-center studies involving complex healthcare data.Competing Interest StatementJuan R. Troncoso-Pastoriza and Jean-Pierre Hubaux are co-founders of the start-up Tune Insight (https://tuneinsight.com). All authors declare no other competing interests.