Computational Attestations of Polynomial Integrity Towards Verifiable Machine-Learning

TL;DR

This paper demonstrates a fast, verifiable method for proving the correctness of differentially-private linear regression training on large datasets, advancing privacy-preserving machine learning services.

Contribution

It introduces a zero-knowledge proof approach for efficiently attesting to the integrity of differentially-private machine learning computations, achieving unprecedented speed for large datasets.

Findings

Proved correct training of DP linear regression on 50,000 samples in under 6 minutes.

Verified the entire computation in 0.17 seconds.

Achieved the fastest known provable-DP result for this dataset size.

Abstract

Machine-learning systems continue to advance at a rapid pace, demonstrating remarkable utility in various fields and disciplines. As these systems continue to grow in size and complexity, a nascent industry is emerging which aims to bring machine-learning-as-a-service (MLaaS) to market. Outsourcing the operation and training of these systems to powerful hardware carries numerous advantages, but challenges arise when privacy and the correctness of work carried out must be ensured. Recent advancements in the field of zero-knowledge cryptography have led to a means of generating arguments of integrity for any computation, which in turn can be efficiently verified by any party, in any place, at any time. In this work we prove the correct training of a differentially-private (DP) linear regression over a dataset of 50,000 samples on a single machine in less than 6 minutes, verifying the entire computation in 0.17 seconds. To our knowledge, this result represents the fastest known instance in the literature of provable-DP over a dataset of this size. We believe this result constitutes a key stepping-stone towards end-to-end private MLaaS.