Homomorphic Encryption (HE) is an emerging encryption scheme that allows computations to be performed directly on encrypted messages. This property provides promising applications such as privacy-preserving deep learning and cloud computing. Prior works have been proposed to enable practical privacy-preserving applications with architectural-aware optimizations on CPUs, CUDA-enabled GPUs and FPGAs. However, there is no systematic optimization for the whole HE pipeline on Intel GPUs. In this paper, we present the first-ever SYCL-based GPU backend for Microsoft SEAL APIs. We perform optimizations from instruction level, algorithmic level and application level to accelerate our HE library based on the Cheon, Kim, Kim and Song (CKKS) scheme on Intel GPUs. The performance is validated on two latest Intel GPUs. Experimental results show that our staged optimizations together with optimizations including low-level optimizations and kernel fusion accelerate the Number Theoretic Transform (NTT), a key algorithm for HE, by up to 9.93X compared with the naive GPU baseline. The roofline analysis confirms that our optimized NTT reaches 79.8% and 85.7% of the peak performance on two GPU devices. Through the highly optimized NTT and the assembly-level optimization, we obtain 2.32X – 3.05X acceleration for HE evaluation routines. In addition, our all-together systematic optimizations improve the performance of encrypted element-wise polynomial matrix multiplication application by up to 3.11X.

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 incurs 100x–10,000x memory and runtime overheads. Secure deep neural network (DNN) inference using HE is currently limited by computing and memory resources, with frameworks requiring hundreds of gigabytes of DRAM to evaluate small models. To overcome these limitations, in this paper we explore the feasibility of leveraging hybrid memory systems comprised of DRAM and persistent memory. In particular, we explore the recently-released Intel® Optane™ PMem technology and the Intel® HE-Transformer nGraph® to run large neural networks such as MobileNetV2 (in its largest variant) and ResNet-50 for the first time in the literature. We present an in-depth analysis of the efficiency of the executions with different hardware and software configurations. Our results conclude that DNN inference using HE incurs on friendly access patterns for this memory configuration, yielding efficient executions.

Privacy-preserving machine learning (PPML) has many applications, from medical image classification and anomaly detection to financial analysis. nGraph-HE enables data scientists to perform private inference of deep learning (DL) models trained using popular frameworks such as TensorFlow. nGraph-HE computes linear layers using the CKKS homomorphic encryption (HE) scheme. The non-polynomial activation functions, such as MaxPool and ReLU, are evaluated in the clear by the data owner who obtains the intermediate feature maps. This leaks the feature maps to the data owner from which it may be possible to deduce the DL model weights. As a result, such protocols may not be suitable for deployment, especially when the DL model is intellectual property.

Advances in customers' data privacy laws create pressures and pain points across the entire lifecycle of AI products. Working figures such as data scientists and data engineers need to account for the correct use of privacy-enhancing technologies such as homomorphic encryption, secure multi-party computation, and trusted execution environment when they develop, test and deploy products embedding AI models while providing data protection guarantees. In this work, we share the lessons learned during the development of frameworks to aid data scientists and data engineers to map their optimized workloads onto privacy-enhancing technologies seamlessly and correctly.

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.