Federated learning-oriented decentralized function encryption privacy protection method and system

Abstract

The invention provides a federated learning-oriented decentration function encryption privacy protection method and system. The method comprises the following steps of: obtaining an initial model, a public data set, an encryption label, an encryption prime number, an encryption weight and a weight vector parameter sent by a server; training the initial model according to the local data set to obtain a local model, and testing the local model according to the public data set to obtain model accuracy; generating an encryption private key and a partial decryption key according to the encryption prime number, and performing function encryption on the local model according to the encryption private key and the encryption label to obtain an encryption model; and sending the encryption model, the partial decryption key and the model accuracy to a server, so that the server performs decryption aggregation on the encryption model according to the partial decryption key, the encryption label, the encryption weight and the model accuracy to obtain a global model. The method ensures that the server cannot obtain the local model of the user, effectively prevents the collusion attack between the third party and the server, and improves the privacy protection strength and the service effect.

Description

technical field [0001] The invention relates to the technical field of federated learning privacy protection, in particular to a decentralized function encryption privacy protection method and system for federated learning. Background technique [0002] With the wide application of federated learning in digital image processing, natural language processing, text speech processing and other fields, on the basis of breaking data islands and providing more accurate services, further solving the problem of privacy leakage in federated learning has gradually become its implementation application. issues of focus. [0003] Existing privacy protection methods applied to federated learning mainly include homomorphic encryption, secure multi-party computation, and functional encryption. A method to update the model, and a method to ensure parameter privacy by adding a trusted third-party entity responsible for generating, managing, and distributing keys, and using functional encrypt...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a decentralized function encryption privacy protection method for federated learning. While ensuring that the server cannot obtain the specific gradient parameters of each user's local training model, the key is generated through the interaction between the server and the client. This method overcomes the problem that existing privacy protection methods rely on trusted third-party entities to generate, manage and distribute keys, effectively prevents the risk of collusion attacks between trusted third parties and servers, and further improves the privacy protection of client models in federated learning Strength and Model Serving Effects

Images