HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption

Seewoo Lee, Garam Lee, Jung Woo Kim, Junbum Shin, Mun Kyu Lee

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

Abstract

Transfer learning is a de facto standard method for efficiently training machine learning models for data-scarce problems by adding and fine-tuning new classification layers to a model pre-trained on large datasets. Although numerous previous studies proposed to use homomorphic encryption to resolve the data privacy issue in transfer learning in the machine learning as a service setting, most of them only focused on encrypted inference. In this study, we present HETAL, an efficient Homomorphic Encryption based Transfer Learning algorithm, that protects the client's privacy in training tasks by encrypting the client data using the CKKS homomorphic encryption scheme. HETAL is the first practical scheme that strictly provides encrypted training, adopting validation-based early stopping and achieving the accuracy of nonencrypted training. We propose an efficient encrypted matrix multiplication algorithm, which is 1.8 to 323 times faster than prior methods, and a highly precise softmax approximation algorithm with increased coverage. The experimental results for five well-known benchmark datasets show total training times of 567-3442 seconds, which is less than an hour.

Original languageEnglish
Pages (from-to)18988-19009
Number of pages22
JournalProceedings of Machine Learning Research
Volume202
StatePublished - 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023

Bibliographical note

Publisher Copyright:
© 2023 Proceedings of Machine Learning Research. All rights reserved.

Fingerprint

Dive into the research topics of 'HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption'. Together they form a unique fingerprint.

Cite this