Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learning. (arXiv:2301.08778v1 [cs.CR])

Split Learning (SL) is a new collaborative learning technique that allows
participants, e.g. a client and a server, to train machine learning models
without the client sharing raw data. In this setting, the client initially
applies its part of the machine learning model on the raw data to generate
activation maps and then sends them to the server to continue the training
process. Previous works in the field demonstrated that reconstructing
activation maps could result in privacy leakage of client …

client continue data encrypted encrypted data machine machine learning machine learning models maps privacy process server sharing split learning train training