Batch Inference on Deep Convolutional Neural Networks With Fully Homomorphic Encryption Using Channel-By-Channel Convolutions

Secure Machine Learning as a Service (MLaaS) is a viable solution where clients seek secure ML computation delegation while protecting sensitive data. We propose an efficient method to securely evaluate deep standard convolutional neural networks based on residue number system variant of Cheon-Kim-K...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on dependable and secure computing 2024-08, p.1-12
Hauptverfasser:	Cheon, Jung Hee, Kang, Minsik, Kim, Taeseong, Jung, Junyoung, Yeo, Yongdong
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Convolutional neural network Convolutional neural networks Cryptography fully homomorphic encryption privacy-preserving machine learning ResNet Servers Single instruction multiple data Throughput Vectors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!