Towards Dynamic End-to-End Privacy Preserving Data Classification

None, None; None, None; None, None

Towards Dynamic End-to-End Privacy Preserving Data Classification

Conference Paper (2018)

Author(s)

Rania Talbi (INSA Lyon)

Sara Bouchenak (INSA Lyon)

Lydia Y. Chen (Zurich Lab, IBM Research)

Affiliation

External organisation

Decision trees Homomorphic encryption Incremental learning Privacy preserving data classification

DOI related publication

https://doi.org/10.1109/DSN-W.2018.00036 Final published version

To reference this document use

https://resolver.tudelft.nl/uuid:04740819-69c5-45a5-acb3-4952b69dca05

More Info

expand_more

Publication Year

2018

Language

English

Affiliation

External organisation

Article number

8416221

Pages (from-to)

73-74

ISBN (electronic)

9781538655955

Event

48th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops, DSN-W 2018 (2018-06-25 - 2018-06-28), Luxembourg City, Luxembourg

Downloads counter

142

Abstract

In this paper we present DAPPLE, a standalone End-to-End privacy preserving data classification service. It allows incremental decision tree learning over encrypted training data continuously sent by multiple data owners, without having access to the actual content of this data. In the same time, the learnt classification model is used to respond to encrypted classification queries while preserving the privacy of the query, the output corresponding to it and the model itself.