Declarative Privacy-Preserving Inference Queries

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guan, Hong, Tiwari, Ansh, Gautier, Summer, Ambrish, Rajan Hari, Zhou, Lixi, Wang, Yancheng, Gupta, Deepti, Yang, Yingzhen, Xiao, Chaowei, Chowdhury, Kanchan, Zou, Jia
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909498363346944
author Guan, Hong
Tiwari, Ansh
Gautier, Summer
Ambrish, Rajan Hari
Zhou, Lixi
Wang, Yancheng
Gupta, Deepti
Yang, Yingzhen
Xiao, Chaowei
Chowdhury, Kanchan
Zou, Jia
author_facet Guan, Hong
Tiwari, Ansh
Gautier, Summer
Ambrish, Rajan Hari
Zhou, Lixi
Wang, Yancheng
Gupta, Deepti
Yang, Yingzhen
Xiao, Chaowei
Chowdhury, Kanchan
Zou, Jia
contents Detecting inference queries running over personal attributes and protecting such queries from leaking individual information requires tremendous effort from practitioners. To tackle this problem, we propose an end-to-end workflow for automating privacy-preserving inference queries including the detection of subqueries that involve AI/ML model inferences on sensitive attributes. Our proposed novel declarative privacy-preserving workflow allows users to specify "what private information to protect" rather than "how to protect". Under the hood, the system automatically chooses privacy-preserving plans and hyper-parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12393
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Declarative Privacy-Preserving Inference Queries
Guan, Hong
Tiwari, Ansh
Gautier, Summer
Ambrish, Rajan Hari
Zhou, Lixi
Wang, Yancheng
Gupta, Deepti
Yang, Yingzhen
Xiao, Chaowei
Chowdhury, Kanchan
Zou, Jia
Databases
Artificial Intelligence
Detecting inference queries running over personal attributes and protecting such queries from leaking individual information requires tremendous effort from practitioners. To tackle this problem, we propose an end-to-end workflow for automating privacy-preserving inference queries including the detection of subqueries that involve AI/ML model inferences on sensitive attributes. Our proposed novel declarative privacy-preserving workflow allows users to specify "what private information to protect" rather than "how to protect". Under the hood, the system automatically chooses privacy-preserving plans and hyper-parameters.
title Declarative Privacy-Preserving Inference Queries
topic Databases
Artificial Intelligence
url https://arxiv.org/abs/2401.12393