Exploiting Unintended Feature Leakage in Collaborative Learning

IEEE Symposium on Security and Privacy, 2019.

Cited by: 100|Bibtex|Views75
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de|arxiv.org

Abstract:

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates.We demonstrate that these updates leak unintended information about participantsu0027 training data and devel...More

Code:

Data:

Your rating :
0

 

Tags
Comments