GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

03/02/2023
by   Josephine Lamp, et al.
0

In this paper we focus on the problem of generating high-quality, private synthetic glucose traces, a task generalizable to many other time series sources. Existing methods for time series data synthesis, such as those using Generative Adversarial Networks (GANs), are not able to capture the innate characteristics of glucose data and, in terms of privacy, either do not include any formal privacy guarantees or, in order to uphold a strong formal privacy guarantee, severely degrade the utility of the synthetic data. Therefore, in this paper we present GlucoSynth, a novel privacy-preserving GAN framework to generate synthetic glucose traces. The core intuition in our approach is to conserve relationships amongst motifs (glucose events) within the traces, in addition to typical temporal dynamics. Moreover, we integrate differential privacy into the framework to provide strong formal privacy guarantees. Finally, we provide a comprehensive evaluation on the real-world utility of the data using 1.2 million glucose traces

READ FULL TEXT

page 7

page 12

page 14

page 16

page 18

page 20

page 22

page 24

research
03/08/2018

Generating Differentially Private Datasets Using GANs

In this paper, we present a technique for generating artificial datasets...
research
06/28/2022

Improving Correlation Capture in Generating Imbalanced Data using Differentially Private Conditional GANs

Despite the remarkable success of Generative Adversarial Networks (GANs)...
research
11/14/2019

Synthetic Event Time Series Health Data Generation

Synthetic medical data which preserves privacy while maintaining utility...
research
09/05/2023

Differentially Private Synthetic Heavy-tailed Data

The U.S. Census Longitudinal Business Database (LBD) product contains em...
research
01/08/2019

Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data

Open data plays a fundamental role in the 21th century by stimulating ec...
research
07/23/2020

Hide-and-Seek Privacy Challenge

The clinical time-series setting poses a unique combination of challenge...
research
07/07/2022

Privacy-Preserving Synthetic Educational Data Generation

Institutions collect massive learning traces but they may not disclose i...

Please sign up or login with your details

Forgot password? Click here to reset