CRLGMLAug 18, 2020

Efficient Private Machine Learning by Differentiable Random Transformations

arXiv:2008.07758v1
Originality Incremental advance
AI Analysis

This work addresses privacy protection for machine learning applications where existing methods are too slow for production use.

The paper tackles the problem of slow training and inference speeds in privacy-preserving machine learning systems by proposing a framework that combines random transformations with arithmetic sharing, achieving high efficiency and low computation cost.

With the increasing demands for privacy protection, many privacy-preserving machine learning systems were proposed in recent years. However, most of them cannot be put into production due to their slow training and inference speed caused by the heavy cost of homomorphic encryption and secure multiparty computation(MPC) methods. To circumvent this, I proposed a privacy definition which is suitable for large amount of data in machine learning tasks. Based on that, I showed that random transformations like linear transformation and random permutation can well protect privacy. Merging random transformations and arithmetic sharing together, I designed a framework for private machine learning with high efficiency and low computation cost.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes