SecBERT: Privacy-preserving pre-training based neural network inference system.
Neural Netw
; 172: 106135, 2024 Apr.
Article
em En
| MEDLINE
| ID: mdl-38271920
ABSTRACT
Pre-trained models such as BERT have made great achievements in natural language processing tasks in recent years. In this paper, we investigate the privacy-preserving pre-training based neural network inference in a two-server framework based on additive secret sharing technique. Our protocol allows a resource-restrained client to request two powerful servers to cooperatively process the natural processing tasks without revealing any useful information about its data. We first design a series of secure sub-protocols for non-linear functions used in BERT model. These sub-protocols are expected to have broad applications and of independent interest. Based on the building sub-protocols, we propose SecBERT, a privacy-preserving pre-training based neural network inference protocol. SecBERT is the first cryptographically secure privacy-preserving pre-training based neural network inference protocol. We show security, efficiency and accuracy of SecBERT protocol through comprehensive theoretical analysis and experiments.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Segurança Computacional
/
Privacidade
Limite:
Humans
Idioma:
En
Revista:
Neural Netw
Assunto da revista:
NEUROLOGIA
Ano de publicação:
2024
Tipo de documento:
Article