Privacy protection federated learning method and device, electronic equipment and storage medium

• Main Authors: WANG YONGJUN, LIU QIANG, LUO SONGWEI, XIE PEIDAI, LIU LIN, ZHAO WENTAO, XIE TAO, SHI JIANGYONG, MA XINGKONG, FU SHAOJING, XIA GEMING, XU FANGLIANG
• Format: Patent
• Language: Chinese; English
• Published: 01.12.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a privacy protection federated learning method and device, electronic equipment and a storage medium, and the method comprises the steps: generating a key set through a key assistant according to a privacy protection federated learning request; acquiring global model parameters, calling the local model and the local data according to the global model parameters and the user side key to learn the global model to obtain first model parameters, encrypting the first model parameters by using the server side key, and sending the encrypted first model parameters to a service provider; calculating an Euclidean distance according to the first model parameter and the reference model parameter through a service provider, and executing aggregation according to the Euclidean distance to obtain a second model parameter; and encrypting the second model parameter by using the user side key, sending the second model parameter to the federated learning participant, and executing the next round of learni