Cargando…
Deep Neural Network Quantization Framework for Effective Defense against Membership Inference Attacks
Machine learning deployment on edge devices has faced challenges such as computational costs and privacy issues. Membership inference attack (MIA) refers to the attack where the adversary aims to infer whether a data sample belongs to the training set. In other words, user data privacy might be comp...
Autores principales: | Famili, Azadeh, Lao, Yingjie |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10538103/ https://www.ncbi.nlm.nih.gov/pubmed/37765778 http://dx.doi.org/10.3390/s23187722 |
Ejemplares similares
-
Defense against membership inference attack in graph neural networks through graph perturbation
por: Wang, Kai, et al.
Publicado: (2022) -
Membership inference attack on differentially private block coordinate descent
por: Riaz, Shazia, et al.
Publicado: (2023) -
Quantization Framework for Fast Spiking Neural Networks
por: Li, Chen, et al.
Publicado: (2022) -
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
por: Coelho, Claudionor N., et al.
Publicado: (2020) -
Quantization and Deployment of Deep Neural Networks on Microcontrollers
por: Novac, Pierre-Emmanuel, et al.
Publicado: (2021)