News

Habilitation of Assist.-Prof. Mag. Dr. Christoph Georg Schütz


IT-Project Data Souvereignty in winter termin 2021/22


Business Intelligence: Washing Gold in Times of Information Overload


See all news.


Campusplan

campusplan_image

You can find us here.




Towards Informed Watermarking of Personal Health Sensor Data for Data Leakage Detection

Authors: S. Gruber, B. Neumayr, C. Fabianek, E. Gringinger, C. Schütz, M. Schrefl
Paper: Grub20a (2020)
Citation: Proceedings of the 19th International Workshop on Digital-forensics and Watermarking, Nov 25-27, 2020, Melbourne, Australia, Springer Verlag, Lecture Notes in Computer Science (LNCS), 2020.
Resources: Copy  (In order to obtain the copy please send an email with subject  Grub20a  to dke.win@jku.at)


Abstract (English):

Users of personal health devices want an easy way to permanently store their personal health sensor data and to share them with physicians and other authorized users, trusting that the data will not be disclosed to third parties. Digital watermarking for data leakage detection aims to prevent the unauthorized disclosure of data by imperceptibly marking the data for each authorized user, so that the authorized user can be identified as the data leaker and be held accountable. In this paper we present an approach for digital watermarking conceived as part of a personal health sensor data management platform. The approach comprises techniques for informed watermark embedding and non-blind watermark detection. Based on a proof-of-concept prototype, the approach is evaluated regarding configurability, robustness, and performance.

Keywords: Medical Sensor Data, Digital Fingerprinting, Time Series Data