Security and privacy in federated learning: A survey

<p>Federated Learning (FL) allows multiple nodes without actually sharing data with other confidential nodes to retrain a common model. This is particularly relevant in healthcare applications, where data such as medical records are private and confidential. Although federated learning avoids...

Ful tanımlama

Kaydedildi:
Detaylı Bibliyografya
Asıl Yazarlar: Dasaradharami Reddy Kandati (Yazar), S Anusha (Yazar)
Materyal Türü: Kitap
Baskı/Yayın Bilgisi: Trends in Computer Science and Information Technology - Peertechz Publications, 2023-08-16.
Konular:
Online Erişim:Connect to this object online.
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!

MARC

LEADER 00000 am a22000003u 4500
001 peertech__10_17352_tcsit_000066
042 |a dc 
100 1 0 |a Dasaradharami Reddy Kandati  |e author 
700 1 0 |a S Anusha  |e author 
245 0 0 |a Security and privacy in federated learning: A survey 
260 |b Trends in Computer Science and Information Technology - Peertechz Publications,   |c 2023-08-16. 
520 |a <p>Federated Learning (FL) allows multiple nodes without actually sharing data with other confidential nodes to retrain a common model. This is particularly relevant in healthcare applications, where data such as medical records are private and confidential. Although federated learning avoids the exchange of actual data, it still remains possible to fight protection on parameter values revealed in the training process or on a generated Machine Learning (ML) model. This study examines FL's privacy and security concerns and deals with several issues related to privacy protection and safety when developing FL systems. In addition, we have detailed simulation results to illustrate the problems under discussion and potential solutions.</p> 
540 |a Copyright © Dasaradharami Reddy Kandati et al. 
546 |a en 
655 7 |a Literature Review  |2 local 
856 4 1 |u https://doi.org/10.17352/tcsit.000066  |z Connect to this object online.