Abstract: The present disclosure provides a privacy computing method based on homomorphic encryption, which includes steps as follows. The ciphertext data is received, where the ciphertext data has a floating-point homomorphic encryption data structure, and the floating-point homomorphic encryption data structure of the ciphertext data includes the ciphertext mantissa, exponent parameter and gain parameter. The gain parameter sets the precision of the floating point corresponding to the ciphertext mantissa. The exponent parameter is adapted to multiplication or division. The artificial intelligence model performs operations on the ciphertext data to return the ciphertext result.

Abstract: The federated learning system includes a moderator and client devices. Each client device performs a method for verifying model update as follows: receiving a hash function and a general model; training a client model according to the general model and raw data; calculating a difference as an update parameter between the general model and the client model, sending the update parameter to the moderator; inputting the update parameter to the hash function to generate a hash value; sending the hash value to other client devices, and receiving other hash values; summing all the hash values to generate a trust value; receiving an aggregation parameter calculated according to the update parameters; inputting the aggregation parameter to the hash function to generate a to-be-verified value; and updating the client model according to the aggregation parameter when the to-be-verified value equals the trust value.

Abstract: A network initialization communication storage system includes a host device coupled to a storage system and an initialization issue analysis system via a network. The host device includes an initialization subsystem coupled to each of a plurality of ports. During network initialization of the host device via the storage system, the initialization subsystem identifies network initialization communications transmitted via the port(s) and the network, filters the network initialization communications to remove a subset of network initialization information and provide filtered network initialization communications, and transmits the filtered network initialization communications for storage in a remote access controller subsystem in the host device.

Abstract: A network initialization monitoring system includes a host device coupled to a storage system and a monitoring system via a network, and including an initialization subsystem coupled to ports. During network initialization of the host device via the storage system, the initialization subsystem provides a first instance of a communication protocol for monitored port(s), and provides a second instance of the communication protocol for a monitoring port. During the network initialization of the host device via the storage system, the first instance of the communication protocol provided for each monitored port provides copies of network initialization communications transmitted via that monitored port and the network to the second instance of the communication protocol provided for the monitoring port, and the second instance of the communication protocol provided for the monitoring port provides the copies of the network initialization communications to the monitoring system.