HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data

Abstract

Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic Encryption (HE), which allows performing computation on encrypted data. Most HE schemes work in a SIMD fashion, and the data packing method can dramatically affect the running time and memory costs. Finding a packing method that leads to an optimal performant implementation is a hard task. We present a simple and intuitive framework that abstracts the packing decision for the user. We explain its underlying data structures and optimizer, and propose a novel algorithm for performing 2D convolution operations. We used this framework to implement an HE-friendly version of AlexNet, which runs in three minutes, several orders of magnitude faster than other state-of-the-art solutions that only use HE.

17 pages, 7 figures

References in corpus (6)

• SoK: Fully Homomorphic Encryption Compilers
• HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
• SEALion: a Framework for Neural Network Inference on Encrypted Data
• Enabling Homomorphically Encrypted Inference for Large DNN Models
• HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
• A methodology for training homomorphicencryption friendly neural networks

Cited by in corpus (4)

• HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
• HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networks
• Efficient Pruning for Machine Learning Under Homomorphic Encryption
• MOFHEI: Model Optimizing Framework for Fast and Efficient Homomorphically Encrypted Neural Network Inference