nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

2018/10/23 by Fabian Boemer, Boemer, Fabian, Yixing Lao +5 · 3 citations
Computer Science · #Advanced Data Storage Technologies #Complexity and Algorithms in Graphs #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.1810.10121

openalex publication_date 2018/10/23 · openalex created_date 2022/08/02 · openalex updated_date 2026/07/28

Abstract

CF 2019 Artifact Evaluation

Cited by

• Network and Compiler Optimizations for Efficient Linear Algebra Kernels in Private Transformer Inference
• Prismo: A Decision Support System for Privacy-Preserving ML Framework Selection
• A Haskell to FHE Transpiler
• Profiling Concurrent Vision Inference Workloads on NVIDIA Jetson -- Extended

Related

• nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
• LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
• Cheetah: Optimizing and Accelerating Homomorphic Encryption for Private Inference
• SoK: Privacy-preserving Deep Learning with Homomorphic Encryption
• HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption