Dokumentdetails
ID
oai:arXiv.org:2403.14111
Thema
Computer Science - Cryptography an... Computer Science - Machine Learnin...Autor
Lee, Seewoo Lee, Garam Kim, Jung Woo Shin, Junbum Lee, Mun-KyuKategorie
Computer Science
Jahr
2024
Auflistungsdatum
26.06.2024
Schlüsselwörter
encrypted machine algorithm learning encryption transfer homomorphicZusammenfassung
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.
;Comment: ICML 2023, Appendix D includes some updates after official publication
Lee, Seewoo,Lee, Garam,Kim, Jung Woo,Shin, Junbum,Lee, Mun-Kyu, 2024, HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish
evaluate provide turkishmmlu questions language
The Measurement of Acculturation in Neuropsychological Evaluations of Hispanic/Latino Individuals across the Lifespan: A Scoping Review of the Literature
evidence review lifespan various validation acculturation measures
