Abstract: Proposed is a federated learning system. The federated learning system comprises: a central server configured to transmit at least one global parameter of a global model to each client device, receive at least one local parameter of a local model trained from each of client devices, and update the global model using the at least one local parameter; and a plurality of client devices configured to train the local model by applying a loss between a predicted value of the global model and a predicted value of the local model possessed by itself to a loss function, and transmit at least one local parameter of the trained local model to the central server.

Abstract: A burglar proof apparatus is provided, wherein locking and unlocking devices are provided within the storage case so that the storage case may not be opened unless the unlocking device is used, whereby burglary can be reliably prevented. The apparatus includes a case body wherein a housing space is formed for the data storage disk and a lock groove is formed on both outer sides thereof, a disk holder including a plurality of guide rails for insertion into the lock groove of the case body, formed on both inner sides thereof, for supporting and housing a width of the data storage disk, and a locking means for controlling the assembly of the disk holder and the case body, including a hanger piece of a protrusion disposed on an inner face of the lock groove, and a leaf spring disposed between guide rails of the disk holder for locking the hanger piece in a through hole.