Related papers: Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learning

Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learning

URL: http://arxiv.org/abs/2301.08778v1
Date: Fri, 20 Jan 2023 19:26:51 GMT
Title: Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learning
Authors: Tanveer Khan, Khoa Nguyen, Antonis Michalas
Abstract summary: Split Learning (SL) is a new collaborative learning technique that allows participants to train machine learning models without the client sharing raw data. Previous works demonstrated that reconstructing activation maps could result in privacy leakage of client data. In this paper, we improve upon previous works by constructing a protocol based on U-shaped SL that can operate on homomorphically encrypted data.
Score: 6.916134299626706
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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 data. In addition to that, existing mitigation techniques that overcome the privacy leakage of SL prove to be significantly worse in terms of accuracy. In this paper, we improve upon previous works by constructing a protocol based on U-shaped SL that can operate on homomorphically encrypted data. More precisely, in our approach, the client applies Homomorphic Encryption (HE) on the activation maps before sending them to the server, thus protecting user privacy. This is an important improvement that reduces privacy leakage in comparison to other SL-based works. Finally, our results show that, with the optimum set of parameters, training with HE data in the U-shaped SL setting only reduces accuracy by 2.65% compared to training on plaintext. In addition, raw training data privacy is preserved.