A Novel User Membership Leakage Attack in Collaborative Deep Learning

Yaoru Mao
Yaoru Mao
Wenbin Zheng
Wenbin Zheng
Danni Yuan
Danni Yuan

WCSP, pp. 1-6, 2019.

Cited by: 1|Bibtex|Views38|DOI:https://doi.org/10.1109/WCSP.2019.8927871
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

Collaborative deep learning can provide high learning accuracy even participanted usersu0027 datasets are small. In the training process, users only share their locally obtained parameters, therefore it is believed that the privacy of usersu0027 original datasets can be protected. However, we present an attack approach against usersu0027 ...More

Code:

Data:

Your rating :
0

 

Tags
Comments