AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing
We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data.
Saved in:
Main Authors: | Ryffel Théo, Tholoniat Pierre, Pointcheval David, Bach Francis |
---|---|
Format: | article |
Language: | EN |
Published: |
Sciendo
2022
|
Subjects: | |
Online Access: | https://doaj.org/article/5d826b5e3d9b49df9f7ebc14cb47bd78 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Privacy-preserving FairSwap: Fairness and privacy interplay
by: Avizheh Sepideh, et al.
Published: (2022) -
Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
by: Jiang Xue, et al.
Published: (2022) -
Making the Most of Parallel Composition in Differential Privacy
by: Smith Josh, et al.
Published: (2022) -
Ulixes: Facial Recognition Privacy with Adversarial Machine Learning
by: Cilloni Thomas, et al.
Published: (2022) -
Circuit-PSI With Linear Complexity via Relaxed Batch OPPRF
by: Chandran Nishanth, et al.
Published: (2022)