Filters








3 Hits in 3.9 sec

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

Claude Rosin Ngueveu, Claude Rosin
2020 arXiv   pre-print
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  ...  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).  ...  The objective of DySan is to protect the user motion sensor data against sensitive attribute inferences while maintaining data utility.  ... 
arXiv:2003.10325v2 fatcat:t7pafxa4tfcztb6ksm7ykexp6y

DySan: Dynamically Sanitizing Motion Sensor Data Against Sensitive Inferences through Adversarial Networks

Antoine Boutet, Carole Frindel, Sébastien Gambs, Théo Jourdan, Rosin Claude Ngueveu
2021 Proceedings of the 2021 ACM Asia Conference on Computer and Communications Security  
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  ...  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  ...  The objective of DySan is to protect the user motion sensor data against sensitive attribute inferences while maintaining data utility.  ... 
doi:10.1145/3433210.3453095 fatcat:cswdovawa5czjnyanotijiwgjy

Ordered physical human activity recognition based on ordinal classification

2021 Turkish Journal of Electrical Engineering and Computer Sciences  
DYSAN: dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks.  ...  Protecting sensory data against sensitive inferences.  ... 
doi:10.3906/elk-2010-75 fatcat:tzrqskmx65arnfgvvkiv2ee57y