TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service

Abstract

Machine learning methods are widely used for a variety of prediction problems. \emph{Prediction as a service} is a paradigm in which service providers with technological expertise and computational resources may perform predictions for clients. However, data privacy severely restricts the applicability of such services, unless measures to keep client data private (even from the service provider) are designed. Equally important is to minimize the amount of computation and communication required between client and server. Fully homomorphic encryption offers a possible way out, whereby clients may encrypt their data, and on which the server may perform arithmetic computations. The main drawback of using fully homomorphic encryption is the amount of time required to evaluate large machine learning models on encrypted data. We combine ideas from the machine learning literature, particularly work on binarization and sparsification of neural networks, together with algorithmic tools to speed-up and parallelize computation using encrypted data.

arXiv commentAccepted at International Conference in Machine Learning (ICML), 2018

References in corpus (9)

• Community detection in graphs
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Trained Ternary Quantization
• Compressing Neural Networks with the Hashing Trick
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• Gazelle: A Low Latency Framework for Secure Neural Network Inference
• Bitwise Neural Networks

Cited by in corpus (13)

• XONN: XNOR-based Oblivious Deep Neural Network Inference
• Privacy in Deep Learning: A Survey
• Security and Privacy Issues in Deep Learning
• Privado: Practical and Secure DNN Inference with Enclaves
• On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks
• nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data
• MOBIUS: Model-Oblivious Binarized Neural Networks
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryption
• Utility/Privacy Trade-off through the lens of Optimal Transport
• A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component
• Towards Efficient and Secure Delivery of Data for Deep Learning with Privacy-Preserving
• Towards Efficient and Secure Delivery of Data for Training and Inference with Privacy-Preserving