An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors

07/02/2018
by   Joshua Allen, et al.
0

Differential privacy has emerged as the main definition for private data analysis and machine learning. The global model of differential privacy, which assumes that users trust the data collector, provides strong privacy guarantees and introduces small errors in the output. In contrast, applications of differential privacy in commercial systems by Apple, Google, and Microsoft, use the local model. Here, users do not trust the data collector, and hence randomize their data before sending it to the data collector. Unfortunately, local model is too strong for several important applications and hence is limited in its applicability. In this work, we propose a framework based on trusted processors and a new definition of differential privacy called Oblivious Differential Privacy, which combines the best of both local and global models. The algorithms we design in this framework show interesting interplay of ideas from the streaming algorithms, oblivious algorithms, and differential privacy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/20/2019

Outis: Crypto-Assisted Differential Privacy on Untrusted Servers

Differential privacy has steadily become the de-facto standard for achie...
research
08/18/2022

Verifiable Differential Privacy For When The Curious Become Dishonest

Many applications seek to produce differentially private statistics on s...
research
03/24/2018

Comparing Population Means under Local Differential Privacy: with Significance and Power

A statistical hypothesis test determines whether a hypothesis should be ...
research
12/18/2019

The power of synergy in differential privacy:Combining a small curator with local randomizers

Motivated by the desire to bridge the utility gap between local and trus...
research
06/25/2023

Locally Differentially Private Distributed Online Learning with Guaranteed Optimality

Distributed online learning is gaining increased traction due to its uni...
research
04/08/2022

Network Shuffling: Privacy Amplification via Random Walks

Recently, it is shown that shuffling can amplify the central differentia...
research
08/03/2021

Bit-efficient Numerical Aggregation and Stronger Privacy for Trust in Federated Analytics

Private data generated by edge devices – from smart phones to automotive...

Please sign up or login with your details

Forgot password? Click here to reset