Toward privacy in IoT mobile devices for activity recognition

Théo Jourdan 1 Antoine Boutet 2 Carole Frindel 3
2 PRIVATICS - Privacy Models, Architectures and Tools for the Information Society
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
3 Images et Modèles
CREATIS - Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé
Abstract : Recent advances in wireless sensors for personal healthcare allow to recognise human real-time activities with mobile devices. While the analysis of those datastreamcanhavemanybenefitsfromahealthpointofview,itcanalsoleadtoprivacy threats by exposing highly sensitive information. In this paper, we propose a privacy-preserving framework for activity recognition. This framework relies on a machine learning technique to efficiently recognise the user activity pattern, useful for personal healthcare monitoring, while limiting the risk of re-identification of users from biometric patterns that characterizes each individual. To achieve that, we rely on a carefully features extraction scheme in both temporal and frequency domainandapplyageneralisation-basedapproachonfeaturesleadingtore-identify users. We extensively evaluate our framework with a reference dataset: results show an accurate activity recognition (87%) while limiting the re-identifation rate (33%). This represents a slightly decrease of utility (9%) against a large privacy improvement (53%) compared to state-of-the-art baselines.
Complete list of metadatas

https://hal.inria.fr/hal-01941453
Contributor : Théo Jourdan <>
Submitted on : Tuesday, December 4, 2018 - 2:38:37 PM
Last modification on : Tuesday, March 5, 2019 - 12:20:38 PM
Long-term archiving on : Tuesday, March 5, 2019 - 12:59:00 PM

File

ppml.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01941453, version 1

Citation

Théo Jourdan, Antoine Boutet, Carole Frindel. Toward privacy in IoT mobile devices for activity recognition. Privacy Preserving Machine Learning NeurIPS 2018 Workshop, Dec 2018, Montréal, Canada. pp.1-6. ⟨hal-01941453⟩

Share

Metrics

Record views

136

Files downloads

104