HE-PEx: Efficient Machine Learning under Homomorphic Encryption using Pruning, Permutation and Expansion

by   Ehud Aharoni, et al.

Privacy-preserving neural network (NN) inference solutions have recently gained significant traction with several solutions that provide different latency-bandwidth trade-offs. Of these, many rely on homomorphic encryption (HE), a method of performing computations over encrypted data. However, HE operations even with state-of-the-art schemes are still considerably slow compared to their plaintext counterparts. Pruning the parameters of a NN model is a well-known approach to improving inference latency. However, pruning methods that are useful in the plaintext context may lend nearly negligible improvement in the HE case, as has also been demonstrated in recent work. In this work, we propose a novel set of pruning methods that reduce the latency and memory requirement, thus bringing the effectiveness of plaintext pruning methods to HE. Crucially, our proposal employs two key techniques, viz. permutation and expansion of the packed model weights, that enable pruning significantly more ciphertexts and recuperating most of the accuracy loss, respectively. We demonstrate the advantage of our method on fully connected layers where the weights are packed using a recently proposed packing technique called tile tensors, which allows executing deep NN inference in a non-interactive mode. We evaluate our methods on various autoencoder architectures and demonstrate that for a small mean-square reconstruction loss of 1.5*10^-5 on MNIST, we reduce the memory requirement and latency of HE-enabled inference by 60


page 5

page 7


FFConv: Fast Factorized Neural Network Inference on Encrypted Data

Homomorphic Encryption (HE), allowing computations on encrypted data (ci...

A2P-MANN: Adaptive Attention Inference Hops Pruned Memory-Augmented Neural Networks

In this work, to limit the number of required attention inference hops i...

CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference

Recently cloud-based graph convolutional network (GCN) has demonstrated ...

Data Privacy with Homomorphic Encryption in Neural Networks Training and Inference

The use of Neural Networks (NNs) for sensitive data processing is becomi...

Convolutional Neural Network with Pruning Method for Handwritten Digit Recognition

CNN model is a popular method for imagery analysis, so it could be utili...

Efficient Representations for Privacy-Preserving Inference

Deep neural networks have a wide range of applications across multiple d...

AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference

Hybrid Privacy-Preserving Neural Network (HPPNN) implementing linear lay...

Please sign up or login with your details

Forgot password? Click here to reset