Cargando…
Edge-Cloud Collaborative Defense against Backdoor Attacks in Federated Learning
Federated learning has a distributed collaborative training mode, widely used in IoT scenarios of edge computing intelligent services. However, federated learning is vulnerable to malicious attacks, mainly backdoor attacks. Once an edge node implements a backdoor attack, the embedded backdoor mode w...
Autores principales: | Yang, Jie, Zheng, Jun, Wang, Haochen, Li, Jiaxing, Sun, Haipeng, Han, Weifeng, Jiang, Nan, Tan, Yu-An |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9921795/ https://www.ncbi.nlm.nih.gov/pubmed/36772101 http://dx.doi.org/10.3390/s23031052 |
Ejemplares similares
-
Backdoor Attack against Face Sketch Synthesis
por: Zhang, Shengchuan, et al.
Publicado: (2023) -
Federated learning in cloud-edge collaborative architecture: key technologies, applications and challenges
por: Bao, Guanming, et al.
Publicado: (2022) -
Backdoor Attack on Deep Neural Networks Triggered by Fault Injection Attack on Image Sensor Interface
por: Oyama, Tatsuya, et al.
Publicado: (2023) -
A Textual Backdoor Defense Method Based on Deep Feature Classification
por: Shao, Kun, et al.
Publicado: (2023) -
Cerclage Septal Ablation for Hypertrophic Cardiomyopathy: Will a Backdoor Attack on the Septum Be Better?
por: Bach, Richard G.
Publicado: (2020)