User Identification from Time Series of Fitness Data

Thomas Marchioro, Thomas Marchioro, Andrei Kazlouski, Andrei Kazlouski, Evangelos Markatos, Evangelos Markatos

2021

Abstract

We explore the threat posed by disclosure of personal fitness information collected by wearable devices. In particular, we study a scenario where an attacker has a list of aggregated records produced by a group of users, which are stored as time series of steps and calories. We introduce a machine learning-based approach to identify one target person in the aggregated data while being in possession of other records from that person. We estimate how accurately an attacker can find the target’s data when aggregated with other users by testing our approach on two public datasets. Our results show that personal fitness data possess identifying capabilities that should be accounted when they are shared or disclosed.

Paper Citation

in Harvard Style

Marchioro T., Kazlouski A. and Markatos E. (2021). User Identification from Time Series of Fitness Data. In Proceedings of the 18th International Conference on Security and Cryptography - Volume 1: SECRYPT, ISBN 978-989-758-524-1, pages 806-811. DOI: 10.5220/0010585008060811

in Bibtex Style

@conference{secrypt21,
author={Thomas Marchioro and Andrei Kazlouski and Evangelos Markatos},
title={User Identification from Time Series of Fitness Data},
booktitle={Proceedings of the 18th International Conference on Security and Cryptography - Volume 1: SECRYPT,},
year={2021},
pages={806-811},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010585008060811},
isbn={978-989-758-524-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Conference on Security and Cryptography - Volume 1: SECRYPT,
TI - User Identification from Time Series of Fitness Data
SN - 978-989-758-524-1
AU - Marchioro T.
AU - Kazlouski A.
AU - Markatos E.
PY - 2021
SP - 806
EP - 811
DO - 10.5220/0010585008060811