Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy

TL;DR

This paper introduces a privacy-preserving transfer learning method using a secure version of Maximum Mean Discrepancy based on homomorphic encryption, enabling data sharing without privacy risks.

Contribution

It proposes a novel Secure MMD (SMMD) that prevents information leakage in federated transfer learning using homomorphic encryption.

Findings

SMMD is secure against data leakage.

SMMD effectively aligns source and target data distributions.

Experimental results show improved model performance with privacy preservation.

Abstract

The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models. However, data is a valuable resource and are always held by different parties in reality. An effective solution to such a data isolation problem is to employ federated learning, which allows multiple parties to collaboratively train a model. In this paper, we propose a Secure version of the widely used Maximum Mean Discrepancy (SMMD) based on homomorphic encryption to enable effective knowledge transfer under the data federation setting without compromising the data privacy. The proposed SMMD is able to avoid the potential information leakage in transfer learning when aligning the source and target data distribution. As a result, both the source domain and target domain can fully utilize their data to build more scalable models. Experimental results demonstrate that our proposed SMMD is secure and effective.