Výsledky vyhledávání

Report

HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption

Autor: Lee, Seewoo, Lee, Garam, Kim, Jung Woo, Shin, Junbum, Lee, Mun-Kyu

Publikováno v: PMLR 202:19010-19035, 2023

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

Externí odkaz: http://arxiv.org/abs/2403.14111

Zobrazit plný text záznamu

Report

Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption

Autor: Lee, Garam, Kim, Minsoo, Park, Jai Hyun, Hwang, Seung-won, Cheon, Jung Hee

Embeddings, which compress information in raw text into semantics-preserving low-dimensional vectors, have been widely adopted for their efficacy. However, recent research has shown that embeddings can potentially leak private information about sensi

Externí odkaz: http://arxiv.org/abs/2210.02574

Zobrazit plný text záznamu

Akademický článek

Non-invasive prediction of massive transfusion during surgery using intraoperative hemodynamic monitoring data

Autor: Kwon, Doyun, Mi Jung, Young, Lee, Hyung-Chul, Kyong Kim, Tae, Kim, Kwangsoo, Lee, Garam, Kim, Dokyoon, Lee, Seung-Bo, Mi Lee, Seung

Publikováno v: In Journal of Biomedical Informatics August 2024 156

Zobrazit plný text záznamu

Report

Dispersion control in pressure-driven flow through bowed rectangular microchannels

Autor: Lee, Garam, Luner, Alan, Marzuola, Jeremy, Harris, Daniel M.

In fully-developed pressure-driven flow, the spreading of a dissolved solute is enhanced in the flow direction due to transverse velocity variations in a phenomenon now commonly referred to as Taylor-Aris dispersion. It is well understood that the ch

Externí odkaz: http://arxiv.org/abs/2101.02062

Zobrazit plný text záznamu