You may have access to the free features available through My Research. You can save searches, save documents, create alerts and more. Please log in through your library or institution to check if you have access.
If you log in through your library or institution you might have access to this article in multiple languages.
Styles include MLA, APA, Chicago and many more. This feature may be available for free if you log in through your library or institution.
You may have access to it for free by logging in through your library or institution.
You may have access to different export options including Google Drive and Microsoft OneDrive and citation management tools like RefWorks and EasyBib. Try logging in through your library or institution to get access to these tools.
Federated learning technique can be used to solve the data isolated island problem. However, in federated learning, the user's original data is not well protected, and the aggregation server which is used to aggregate gradients can modify aggregated gradient to generate a wrong model or collude with some users to get the privacy data from other honest users. This paper presents a secure federated learning scheme based on secret sharing and aggregated signatures. The scheme deals with the gradient of users by secret sharing algorithm to ensure its security, and uses the aggregate signature to verify the gradient to make sure that the aggregate server can not tamper with the gradients of users. The scheme has high precision, and compared with other similar schemes, the efficiency is improved by about 6%.
