Encrypted state addition computing device and system for federated learning and privacy computing

Abstract

The present application relates to a secret-state addition calculation device and system for federated learning and privacy calculation. The calculation device includes: at least one layer of Montgomery field modular multiplication operation module, configured to perform Montgomery field multiplication operation and Montgomery field modular multiplication operation on multiple ciphertexts of the same batch, and output Montgomery field modular multiplication of multiple ciphertexts Operation result. The at least one layer of Montgomery domain modular multiplication operation module includes a first layer of Montgomery domain modular multiplication operation module, which includes a plurality of parallel modular multiplication calculation engines and a first layer data distribution module connected thereto. The first-layer data distribution module is configured to send one of the multiple ciphertexts each time and selects one of the multiple modular multiplication calculation engines to receive the sent ciphertext in a polling manner, and is also configured to send all the ciphertexts. A batch completion signal is generated and sent to each of the plurality of modular multiplication calculation engines. In this way, resource utilization efficiency and parallel computing speed are improved.

Description

technical field [0001] The present application relates to the technical field of data security and privacy protection, and in particular to a device and system for encrypted state addition computing for federated learning and privacy computing. Background technique [0002] With the development of application fields such as artificial intelligence and big data mining analysis, the demand for data volume is increasing. For example, training artificial intelligence application models requires a large amount of training data with appropriate data labels or feature values. High-quality data often come from the application data generated and accumulated in business activities. However, application data is often scattered in the hands of different organizations and individuals. For example, transaction data is scattered in various financial institutions, and medical diagnosis data is scattered in various medical institutions. Cross-industry and cross-field application data are o...

AI Technical Summary

Problems solved by technology

With the importance of data ownership, user privacy, and data security receiving more attention, and as laws and regulations impose stricter constraints and requirements on data collection and processing, organizations or individuals who control application data are often unwilling or not suitable means to cooperate with each other, making it difficult for the application data held by each to work together

Images