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.
Guardado en:
Autores principales: | Ryffel Théo, Tholoniat Pierre, Pointcheval David, Bach Francis |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Sciendo
2022
|
Materias: | |
Acceso en línea: | https://doaj.org/article/5d826b5e3d9b49df9f7ebc14cb47bd78 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Privacy-preserving FairSwap: Fairness and privacy interplay
por: Avizheh Sepideh, et al.
Publicado: (2022) -
Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
por: Jiang Xue, et al.
Publicado: (2022) -
Making the Most of Parallel Composition in Differential Privacy
por: Smith Josh, et al.
Publicado: (2022) -
Ulixes: Facial Recognition Privacy with Adversarial Machine Learning
por: Cilloni Thomas, et al.
Publicado: (2022) -
Circuit-PSI With Linear Complexity via Relaxed Batch OPPRF
por: Chandran Nishanth, et al.
Publicado: (2022)