Props for Machine-Learning Security

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Juels, Ari, Koushanfar, Farinaz
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913565576790016
author Juels, Ari
Koushanfar, Farinaz
author_facet Juels, Ari
Koushanfar, Farinaz
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20522
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Props for Machine-Learning Security
Juels, Ari
Koushanfar, Farinaz
Cryptography and Security
Artificial Intelligence
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.
title Props for Machine-Learning Security
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2410.20522