Home // SECURWARE 2021, The Fifteenth International Conference on Emerging Security Information, Systems and Technologies // View article

Differential Privacy Approaches in a Clinical Trial

Authors:
Martin Leuckert
Antao Ming

Keywords: Differential Privacy; Clinical Trial; Sensor Data; Machine Learning; Privacy Preservation; Data Security

Abstract:
Clinical trials are essential for advancements in the medical field. The study subjects of clinical trials agree that the data may be used within the scope of the clinical trial and they trust the study center to not misuse the data. Limiting access and anonymizing the data is usually the only way of offering privacy to the subjects. Currently, the collected data may only be used within the scope of the respective study, and in the case of external entities evaluating the data, potential privacy risks occur. To improve the situation, we investigated the applicability of Differential Privacy approaches for clinical trials by looking into differentially private queries as well as differentially private Machine-Learning approaches. Different configurations have been tested for two Differential Privacy mechanisms. The Laplacian Mechanism is much more influenced by the chosen epsilon compared to the Functional Mechanism implemented in this study. However, both mechanisms trade accuracy for privacy. In summary, both queries and Machine Learning can be made secure by applying differential privacy approaches, but the implementation and configuration overhead is still likely to exceed the capacity of clinical trials, especially the smaller ones.

Pages: 24 to 30

Copyright: Copyright (c) IARIA, 2021

Publication date: November 14, 2021

Published in: conference

ISSN: 2162-2116

ISBN: 978-1-61208-919-5

Location: Athens, Greece

Dates: from November 14, 2021 to November 18, 2021