Asynchronous federated learning privacy protection method and system, medium, equipment and terminal

The invention belongs to the technical field of machine learning security, and discloses an asynchronous federated learning privacy protection method and system, a medium, equipment and a terminal, the system is initialized, and random parameters, public series parameters and signature public keys are selected; the user generates a signature and a public-private key pair and sends the signature and the public-private key pair to the server, and the server packages user identity information and a public key and broadcasts the packaged information to other users; after the user receives the data, generating a sub-secret corresponding to the random parameter and a one-time session key; generating a shared key between users and encrypting user information; the to-be-encrypted information of the user is weighted local information of the user; the user sends the masked data to a server, and the server aggregates the data to obtain an aggregation result; and the server divides the aggregation result by the total num