Anti-fraud identification system and method based on cross-domain data analysis

Abstract

The invention provides an anti-fraud identification system and method based on cross-domain data analysis, and relates to the technical field of security computing, the system comprises at least two participating nodes and a hub node, the participating nodes are connected with each other, and the hub node is embedded in one of the participating nodes; the hub node is used for coordinating all the participating nodes for connection and issuing tasks to the participating nodes; wherein the task starts to be executed from the participation node embedded with the hub node, and after all the participation nodes participating in the task are traversed in sequence, the participation node embedded with the hub node carries out decryption, and then the task is executed. And the hub node broadcasts an anti-fraud identification result of the task to all the participating nodes participating in the task. The method is low in requirement on equipment performance, has advancement and portability from the aspects of structure and algorithm, and overcomes the defect that the application range of federal learning is narrow.

Description

technical field [0001] The invention relates to the technical field of secure computing, in particular to an anti-fraud identification system and method based on cross-domain data analysis. Background technique [0002] At present, there are two ways to prevent fraud and prevent user privacy leakage through joint cross-domain data: the first is to send an encrypted ID acquisition request based on the encryption server, and the ID encryption and decryption server returns the encrypted ID after receiving the above request. However, the first solution has higher requirements for hardware, and has no obvious protective effect on cross-domain data, especially banking and insurance industry data with the characteristics of data islands; the second solution is for banking and operations The data on the business side is modeled by completing customer portraits, but the second scheme is mainly applied to vertical federated learning. Vertical federated learning is to splicing two data...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides an anti-fraud identification system and method based on cross-domain data analysis, which is used to solve the defects in the prior art that cannot be applied to cross-domain data anti-fraud, and realizes that the requirements for equipment performance are relatively low, and the structure and algorithm It is said to have its advanced nature and portability, and expand the disadvantages of the narrow application range of federated learning

Images