A Federated Learning Method Based on Differential Privacy and Chaos Encryption

Abstract

A federated learning method based on differential privacy and chaotic encryption. In order to protect the local data information of the computing node from being leaked, in the iterative process, the node adopts the optimization algorithm based on differential privacy to train the model with local data, and then uses the chaotic encryption algorithm to encrypt the updated local model parameters, and the local The model parameter ciphertext is uploaded to the parameter server. The parameter server uses the encrypted model parameters uploaded by multiple computing nodes to update the global model parameters, and sends the updated ciphertext of the global model parameters to each computing node. Next, the computing node decrypts the received global model parameter ciphertext and loads it into the local model for the next iterative training.

Description

technical field [0001] The invention belongs to the cross technical field of information security and artificial intelligence, and particularly relates to a training method based on a federated learning model. Background technique [0002] Federated machine learning (Federated learning / Federated Learning) is a distributed learning algorithm that can train machine learning models on multiple decentralized databases or servers. These devices do not share the data stored in the local database, but share their local Trained model parameters. [0003] In a federated learning system, the parameter server sends an initialized deep learning model to multiple computing nodes. Then, each computing node uses the data in the local database to train the local model, and after training once, sends the calculated model parameter gradient to the parameter server. After receiving the gradient parameters sent by each computing node, the parameter server uses the stochastic gradient descent ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problems of data privacy leakage of computing nodes and high computational cost of privacy protection in the federated learning system, and provide a federated learning method based on differential privacy and chaotic encryption

Images