DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks

Abstract

With the widespread development of the quantified-self movement, an increasing number of users rely on mobile applications to monitor their physical activity through their smartphones. However, granting applications a direct access to sensor data exposes users to privacy risks. In particular, motion sensor data are usually transmitted to analytics applications hosted in the cloud, which leverages on machine learning models to provide feedback on their activity status to users. In this setting, nothing prevents the service provider to infer private and sensitive information about a user such as health or demographic attributes. To address this issue, we propose DySan, a privacy-preserving framework to sanitize motion sensor data against unwanted sensitive inferences (i.e., improving privacy) while limiting the loss of accuracy on the physical activity monitoring (i.e., maintaining data utility). Our approach is inspired from the framework of Generative Adversarial Networks to sanitize the sensor data for the purpose of ensuring a good trade-off between utility and privacy. More precisely, by learning in a competitive manner several networks, DySan is able to build models that sanitize motion data against inferences on a specified sensitive attribute (e.g., gender) while maintaining an accurate activity recognition. DySan builds various sanitizing models, characterized by different sets of hyperparameters in the global loss function, to propose a transfer learning scheme over time by dynamically selecting the model which provides the best utility and privacy trade-off according to the incoming data. Experiments conducted on real datasets demonstrate that DySan can drastically limit the gender inference up to 41% (from 98% with raw data to 57% with sanitized data) while only reducing the accuracy of activity recognition by 3% (from 95% with raw data to 92% with sanitized data).
Fichier principal
Vignette du fichier
DySan_AsiaCCS (2).pdf (1.6 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02512640 , version 1 (23-03-2020)
hal-02512640 , version 2 (20-10-2020)
hal-02512640 , version 3 (24-01-2022)

Identifiers

Cite

Antoine Boutet, Carole Frindel, Sébastien Gambs, Théo Jourdan, Rosin Claude Ngueveu. DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks. ACM ASIACCS 2021 - 16th ACM ASIA Conference on Computer and Communications Security, Jun 2021, Hong Kong (Virtuel), China. ⟨10.1145/3433210.3453095⟩. ⟨hal-02512640v3⟩
319 View
355 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More