Props for Machine-Learning Security

TL;DR

This paper introduces 'props', a new method for secure, privacy-preserving access to deep-web data in machine learning, enabling trustworthy data use and overcoming data scarcity issues.

Contribution

The paper presents 'props', a novel approach utilizing privacy-preserving oracle systems to facilitate secure, trustworthy access to deep-web data for ML applications.

Findings

Enables secure access to deep-web data for ML

Supports privacy-preserving inference with sensitive data

Leverages blockchain-based oracle systems

Abstract

We propose protected pipelines or props for short, a new approach for authenticated, privacy-preserving access to deep-web data for machine learning (ML). By permitting secure use of vast sources of deep-web data, props address the systemic bottleneck of limited high-quality training data in ML development. Props also enable privacy-preserving and trustworthy forms of inference, allowing for safe use of sensitive data in ML applications. Props are practically realizable today by leveraging privacy-preserving oracle systems initially developed for blockchain applications.