5 papers
Accelerating Encrypted Computing on Intel GPUs
Yujia Zhai, Mohannad Ibrahim, Yiqin Qiu +4
Homomorphic Encryption (HE) is an emerging encryption scheme that allows computations to be performed directly on encrypted messages. This property provides promising applications…
Enabling Homomorphically Encrypted Inference for Large DNN Models
Guillermo Lloret-Talavera, Marc Jorda, Harald Servat +5
The proliferation of machine learning services in the last few years has raised data privacy concerns. Homomorphic encryption (HE) enables inference using encrypted data but it inc…
Intel HEXL: Accelerating Homomorphic Encryption with Intel AVX512-IFMA52
Fabian Boemer, Sejun Kim, Gelila Seifu +2
Modern implementations of homomorphic encryption (HE) rely heavily on polynomial arithmetic over a finite field. This is particularly true of the CKKS, BFV, and BGV HE schemes. Two…
nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
Fabian Boemer, Anamaria Costache, Rosario Cammarota +1
In previous work, Boemer et al. introduced nGraph-HE, an extension to the Intel nGraph deep learning (DL) compiler, that enables data scientists to deploy models with popular frame…
nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data
Fabian Boemer, Yixing Lao, Rosario Cammarota +1
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). Howeve…