Data security sharing method based on hash map and federated learning

Abstract

The invention discloses a data security sharing method based on a hash map and federated learning. Detection of a federated learning local model is added into a hashgraph consensus algorithm of a block chain 3.0 technology; dishonest nodes are prevented from providing an error model; meanwhile, the federated learning data model is realized through a method of carrying out weighted aggregation on alocal model. The method comprises the following steps: 1) adding detection on the federated learning local model into a block chain 3.0 technology hash graph consensus algorithm to prevent dishonestnodes from providing an error model; and 2) the dishgraph node detection process mainly comprising the following steps of: generating an event, performing Gossip communication, performing consensus byadopting a virtual voting algorithm, and realizing successful detection of dishonest nodes in a federal learning process based on a data security sharing model of hash and federal learning.

Description

technical field [0001] The invention designs a data security sharing method based on hashgraph and federated learning, which is suitable for mobile edge computing network and belongs to the field of information communication technology. Background technique [0002] As COVID-19 is out of control, it is particularly important to trace the contacts of patients with new crowns. Statistical analysis of many content such as contacts, which involves the privacy data of many users, so it is impossible to upload all the data to the cloud for model training. Therefore, it is necessary to use federated learning to solve this problem, which is aggregated on the client [1 ] on the locally trained model and obtain a central model on the server. In federated learning, distributed local devices compute local models based on local data samples and send them to a central server. A central server trains a shared model by aggregating local models from different devices [2]. Therefore, durin...

AI Technical Summary

Problems solved by technology

[0004] Technical problem: The present invention proposes a data security sharing method based on hashgraph and federated learning in the process of COVID-19 epidemic prevention and control, which solves the problem that dishonest model providers have adverse effects on model generation in the federated learning process, and improves the Accuracy of federated learning training

Images