TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
This addresses data privacy and efficiency challenges for clients using encrypted prediction services, representing an incremental improvement over existing methods.
The paper tackles the problem of slow encrypted prediction in machine learning as a service by combining binarization, sparsification, and algorithmic optimizations to accelerate computations, though no concrete performance numbers are provided in the 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.