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

S. Gruber, B. Neumayr, C. Fabianek, E. Gringinger, C. Schütz, M. Schrefl
Grub20a (2020)
Proceedings of the 19th International Workshop on Digital-forensics and Watermarking (IWDW 2020), Nov 25-27, 2020, Melbourne, Australia, Editor(s): X. Zhao, Y.-Q. Shi, A. Piva, H. J. Kim, Springer Verlag, Lecture Notes in Computer Science (LNCS Vol, 12617), ISBN ISBN: 978-3-030-69449-4, DOI:, 2020.
Kopie  (Senden Sie ein Email mit  Grub20a  als Betreff an um diese Kopie zu erhalten)

Kurzfassung (Englisch)

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