Cryptology ePrint Archive: Report 2019/350

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

Fabian Boemer and Yixing Lao and Rosario Cammarota and Casimir Wierzynski

Abstract: Homomorphic encryption (HE)---the ability to perform computation on encrypted data---is an attractive remedy to increasing concerns about data privacy in deep learning (DL). However, building DL models that operate on ciphertext is currently labor-intensive and requires simultaneous expertise in DL, cryptography, and software engineering. DL frameworks and recent advances in graph compilers have greatly accelerated the training and deployment of DL models to various computing platforms. We introduce nGraph-HE, an extension of nGraph, Intel's DL graph compiler, which enables deployment of trained models with popular frameworks such as TensorFlow while simply treating HE as another hardware target. Our graph-compiler approach enables HE-aware optimizations-- implemented at compile-time, such as constant folding and HE-SIMD packing, and at run-time, such as special value plaintext bypass. Furthermore, nGraph-HE integrates with DL frameworks such as TensorFlow, enabling data scientists to benchmark DL models with minimal overhead.

Category / Keywords: implementation / Homomorphic encryption, intermediate representation, deep learning

Original Publication (in the same form): To appear in Computing Frontiers 2019

Date: received 1 Apr 2019, last revised 2 Apr 2019

Contact author: fabian boemer at intel com

Available format(s): PDF | BibTeX Citation

Version: 20190403:020824 (All versions of this report)

Short URL:

[ Cryptology ePrint archive ]