ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipeline

by   Haodi Wang, et al.

Machine Learning as a service (MLaaS) permits resource-limited clients to access powerful data analytics services ubiquitously. Despite its merits, MLaaS poses significant concerns regarding the integrity of delegated computation and the privacy of the server's model parameters. To address this issue, Zhang et al. (CCS'20) initiated the study of zero-knowledge Machine Learning (zkML). Few zkML schemes have been proposed afterward; however, they focus on sole ML classification algorithms that may not offer satisfactory accuracy or require large-scale training data and model parameters, which may not be desirable for some applications. We propose ezDPS, a new efficient and zero-knowledge ML inference scheme. Unlike prior works, ezDPS is a zkML pipeline in which the data is processed in multiple stages for high accuracy. Each stage of ezDPS is harnessed with an established ML algorithm that is shown to be effective in various applications, including Discrete Wavelet Transformation, Principal Components Analysis, and Support Vector Machine. We design new gadgets to prove ML operations effectively. We fully implemented ezDPS and assessed its performance on real datasets. Experimental results showed that ezDPS achieves one-to-three orders of magnitude more efficient than the generic circuit-based approach in all metrics while maintaining more desirable accuracy than single ML classification approaches.


page 1

page 2

page 3

page 4


VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a Service

Machine Learning as a Service (MLaaS) allows clients with limited resour...

Chiron: Privacy-preserving Machine Learning as a Service

Major cloud operators offer machine learning (ML) as a service, enabling...

HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models

Machine learning (ML) algorithms are increasingly important for the succ...

Data and Model Dependencies of Membership Inference Attack

Machine Learning (ML) techniques are used by most data-driven organisati...

PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models

The ubiquitous use of machine learning algorithms brings new challenges ...

UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification

Machine Learning (ML) research has focused on maximizing the accuracy of...

Sound Event Classification in an Industrial Environment: Pipe Leakage Detection Use Case

In this work, a multi-stage Machine Learning (ML) pipeline is proposed f...

Please sign up or login with your details

Forgot password? Click here to reset