LHDNN: Maintaining High Precision and Low Latency Inference of Deep Neural Networks on Encrypted Data

LHDNN: Maintaining High Precision and Low Latency Inference of Deep Neural Networks on Encrypted Data

The advancement of deep neural networks (DNNs) has prompted many cloud service providers to offer deep learning as a service (DLaaS) to users across various application domains. However, in current DLaaS prediction systems, users’ data are at risk of leakage. Homomorphic encryption allows operations...

Full description

Bibliographic Details
Main Authors: Jiaming Qian, Ping Zhang, Haoyong Zhu, Muhua Liu, Jiechang Wang, Xuerui Ma
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Applied Sciences
Subjects:
DLaaS
homomorphic encryption
privacy protection
CKKS FHE scheme
deep neural networks
hermite polynomials
Online Access:https://www.mdpi.com/2076-3417/13/8/4815

Internet

https://www.mdpi.com/2076-3417/13/8/4815

Similar Items