HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption

arXiv:2403.14111v1 Announce Type: cross
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 …

abstract arxiv classification cs.cr cs.lg data data privacy datasets encryption fine-tuning homomorphic encryption issue large datasets machine machine learning machine learning models privacy standard studies training transfer transfer learning type