Masking Feedforward Neural Networks Against Power Analysis Attacks
Recent advances in machine learning have enabled Neural Network (NN) inference directly on constrained embedded devices. This local approach enhances the privacy of user data, as the inputs to the NN inference are not shared with third-party cloud providers over a communication network. At the same...
Guardado en:
Autores principales: | Athanasiou Konstantinos, Wahl Thomas, Ding A. Adam, Fei Yunsi |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Sciendo
2022
|
Materias: | |
Acceso en línea: | https://doaj.org/article/6c1c8759e6a64fc0854425b0d7278bbc |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Editors’ Introduction
por: Kerschbaum Florian, et al.
Publicado: (2022) -
Disparate Vulnerability to Membership Inference Attacks
por: Kulynych Bogdan, et al.
Publicado: (2022) -
Zen and the art of model adaptation: Low-utility-cost attack mitigations in collaborative machine learning
por: Usynin Dmitrii, et al.
Publicado: (2022) -
If You Like Me, Please Don’t “Like” Me: Inferring Vendor Bitcoin Addresses From Positive Reviews
por: Schäfer Jochen, et al.
Publicado: (2022) -
Differentially private partition selection
por: Desfontaines Damien, et al.
Publicado: (2022)