Federated unlearning method based on malicious terminal intervention training

A federated unlearning method based on malicious terminal intervention training, comprising the following steps:

• step 1:
• building an FL framework, constructing a convolutional neural network model, and setting clients C={C1, C2, . . . , CN} involved in training and local training data D={D1, D2, . . . , DN} of the clients, wherein CN is a malicious client;
• step 2:
• improving the setting of experimental parameters, storing a benchmark dataset Db in a central server, then performing FL training, recording each round of training parameter update ΔM of the malicious client in the central server, finally obtaining a final global model MT and conducting tests to obtain a predicting score acc(MT);
• step 3:
• loading the final global model MT obtained in step 2 and the parameter updates of the malicious client, performing unlearning operation, establishing an unlearning model MT′, setting the parameters as the parameters of the final global model minus each round of parameter update of the malicious client, and deciding whether to terminate the unlearning operation in advance by judging the predicting score of the unlearning model;
• step 4:
• loading the unlearning model MT′ obtained in step 3, performing normal training on the unlearning model using the benchmark dataset for a specified number of times to recover model performance deviations produced when performing the unlearning operation, and finally outputting the unlearning model at this moment as a final model;
• step 5:
• loading the model obtained in step 4, inputting data test set images for testing the model into the trained final unlearning model, and after obtaining the corresponding predicting score, determining the performance of the model.