| Texto completo | |
| Autor(es): |
Neumann, Leonardo
;
Guimaraes, Antonio
;
Aranha, Diego F.
;
Borin, Edson
Número total de Autores: 4
|
| Tipo de documento: | Artigo Científico |
| Fonte: | APPLIED CRYPTOGRAPHY AND NETWORK SECURITY, ACNS 2025, PT III; v. 15827, p. 30-pg., 2025-01-01. |
| Resumo | |
Homomorphic encryption (HE) enables privacy-preserving machine learning by allowing computation directly over encrypted data, and HE-based inference algorithms are already practical even for relatively large Convolutional Neural Networks (CNNs). Encrypted training, on the other hand, is still a major challenge, with current solutions taking up to weeks of computation. In this paper, we introduce a framework for training and inference on Weightless Neural Network (WNN) models over encrypted data. Compared to CNNs, we show (HE-based) WNNs offer much better performance with a relatively small accuracy loss. Our solution is based on new building blocks we introduce for the TFHE scheme that can be of independent interest. We achieve 91.71% accuracy on the MNIST dataset after only 3.5 min of encrypted training (multi-threaded), going up to 93.76% in 3.5 h. Compared to the state of the art on HE-based CNN training, Glyph (Lou et al., NeurIPS 2020), this represents a speedup of up to 1200 times with an accuracy loss of at most 5.4%. For the HAM10000 dataset, we achieve 67.85% accuracy in just 1.5 min, going up to 69.85% after 1 h, which represents a 0.65% accuracy improvement while being 60 times faster than Glyph. We also provide solutions for small-scale encrypted training. In a single thread using less than 200 MB of memory, we train over the entire Wisconsin Breast Cancer dataset in just 11 s achieving 97.3% accuracy. (AU) | |
| Processo FAPESP: | 13/08293-7 - CECC - Centro de Engenharia e Ciências Computacionais |
| Beneficiário: | Munir Salomao Skaf |
| Modalidade de apoio: | Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs |
| Processo FAPESP: | 19/12783-6 - Migração eficiente de aplicações científicas e de engenharia de alto desempenho para a nuvem |
| Beneficiário: | Antonio Carlos Guimarães Junior |
| Modalidade de apoio: | Bolsas no Brasil - Doutorado |