Skip to Main content Skip to Navigation
Conference papers

Towards Practical Privacy-Preserving Collaborative Machine Learning at a Scale

Rania Talbi 1
1 DRIM - Distribution, Recherche d'Information et Mobilité
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Collaborative machine learning allows multiple participants to get a global and valuable insight over their joint data. Nonetheless, in data-sensitive applications, it is crucial to maintain confidentiality across the end-to-end path the data follows from model training phase to the inference phase, preventing any form of information leakage about training data, the learned model, or the inference queries. In this paper, we present our approach to address this problem through PrivML, a framework for end-to-end outsourced privacy-preserving data classification over encrypted data. We provide some preliminary results comparing our proposal with state of the art solutions as well as some insight on our prospective research plan.
Complete list of metadata

Cited literature [7 references]  Display  Hide  Download
Contributor : Rania Talbi <>
Submitted on : Wednesday, July 8, 2020 - 11:21:38 AM
Last modification on : Thursday, July 9, 2020 - 3:37:20 AM
Long-term archiving on: : Wednesday, September 23, 2020 - 10:52:44 PM


Files produced by the author(s)



Rania Talbi. Towards Practical Privacy-Preserving Collaborative Machine Learning at a Scale. 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, Jun 2020, València, Spain. ⟨10.1109/DSN-S50200.2020.00037⟩. ⟨hal-02886063⟩



Record views


Files downloads