View source for Jinan University (20240256900). METHOD FOR BUILDING BLOCKCHAIN-BASED SECURE AGGREGATION IN FEDERATED LEARNING WITH DATA REMOVAL simplified abstract

=METHOD FOR BUILDING BLOCKCHAIN-BASED SECURE AGGREGATION IN FEDERATED LEARNING WITH DATA REMOVAL=


==Organization Name==

[[:Category:Jinan University|Jinan University]]


[[Category:Jinan University]]

==Inventor(s)==

[[:Category:Jiasi Weng of Guangzhou (CN)|Jiasi Weng of Guangzhou (CN)]][[Category:Jiasi Weng of Guangzhou (CN)]]

[[:Category:Yongdong Wu of Guangzhou (CN)|Yongdong Wu of Guangzhou (CN)]][[Category:Yongdong Wu of Guangzhou (CN)]]

[[:Category:Jian Weng of Guangzhou (CN)|Jian Weng of Guangzhou (CN)]][[Category:Jian Weng of Guangzhou (CN)]]

[[:Category:Ming Li of Guangzhou (CN)|Ming Li of Guangzhou (CN)]][[Category:Ming Li of Guangzhou (CN)]]

[[:Category:Jianan Liu of Guangzhou (CN)|Jianan Liu of Guangzhou (CN)]][[Category:Jianan Liu of Guangzhou (CN)]]

[[:Category:Anjia Yang of Guangzhou (CN)|Anjia Yang of Guangzhou (CN)]][[Category:Anjia Yang of Guangzhou (CN)]]

[[:Category:Yejian Liang of Guangzhou (CN)|Yejian Liang of Guangzhou (CN)]][[Category:Yejian Liang of Guangzhou (CN)]]

==METHOD FOR BUILDING BLOCKCHAIN-BASED SECURE AGGREGATION IN FEDERATED LEARNING WITH DATA REMOVAL - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240256900 titled 'METHOD FOR BUILDING BLOCKCHAIN-BASED SECURE AGGREGATION IN FEDERATED LEARNING WITH DATA REMOVAL

The patent application describes a method, device, and system for building blockchain-based secure aggregation in federated learning with data removal.

* Selecting a first quantity of client nodes to participate in an iteration.
* Sending a list of selected client nodes to each of the first quantity of client nodes.
* Acquiring model training information transmitted by a second quantity of client nodes in encrypted form.
* Aggregating the encrypted model training information to obtain an aggregate result.
* Broadcasting a list of client nodes and the aggregate result via a blockchain.

Potential Applications:
- Secure aggregation in federated learning systems.
- Data privacy protection in collaborative machine learning environments.

Problems Solved:
- Ensuring secure aggregation of model training information.
- Protecting sensitive data during federated learning processes.

Benefits:
- Enhanced data privacy and security.
- Efficient collaboration in federated learning settings.

Commercial Applications:
Title: "Secure Federated Learning Aggregation System"
This technology can be used in industries such as healthcare, finance, and telecommunications to securely aggregate model training information in collaborative learning environments, ensuring data privacy and security.

Questions about Secure Federated Learning Aggregation System:
1. How does this technology improve data privacy in federated learning systems?
- This technology enhances data privacy by securely aggregating model training information using blockchain-based encryption methods.

2. What are the potential implications of this technology in industries like healthcare and finance?
- This technology can revolutionize data collaboration in sensitive industries by ensuring secure aggregation of model training information while protecting data privacy.


==Original Abstract Submitted==

method, device and system for building blockchain-based secure aggregation in federated learning with data removal are provided. the method includes: selecting a first quantity of client nodes, to participate in an i-th iteration; sending a list of the selected client nodes to each of the first quantity of client nodes; acquiring model training information transmitted by each of a second quantity of client nodes, the model training information being transmitted in a form of cypher text, where the cypher text is generated by performing homomorphic encryption on the model training information based on pairwise seeds computed for each of the first quantity of client nodes from a symmetric bivariate polynomial and a private seed computed from asymmetric bivariate polynomial; aggregating the cypher text to obtain an aggregate result; and broadcasting a list of the second quantity of client nodes and the aggregate result via a blockchain.



[[Category:G06N3/098]]
[[Category:CPC_G06N3/098]]