Fully homomorphic encryption deep learning reasoning method and system based on FPGA

Abstract

The invention discloses a fully homomorphic encryption deep learning reasoning method and system based on an FPGA. The method comprises the steps of obtaining a ciphertext encrypted by a homomorphic encryption algorithm and a coded plaintext; obtaining the multiplication depth, the data processing scale and the network layer of the initial deep learning network; determining a value range of a coefficient module factor of the polynomial according to the term number of the plaintext polynomial, determining the number of values according to the multiplication depth, and determining a coefficient module according to the coefficient module factor selected by the error parameter; determining the weight and deviation of the network layer according to the item number and coefficient module of the polynomial and the data processing scale so as to obtain a packaging strategy of the network layer; according to the packaging strategy and the plaintext, selection of the item number and the coefficient module of the polynomial is judged, a network layer is optimized, an inference model is constructed, and therefore a ciphertext inference result is output to the ciphertext. An accelerator is integrally designed for the combination of homomorphic encryption and a deep learning network by using an FPGA, so that the reasoning speed of homomorphic encryption data on the deep learning network is increased.

Description

technical field [0001] The invention relates to the technical field of homomorphic encryption algorithms, in particular to an FPGA-based fully homomorphic encryption deep learning reasoning method and system. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Deep learning (Deep Learning) is a method of machine learning (Machine Learning), and machine learning is a branch of artificial intelligence. Deep learning uses multiple processing layers (neural networks) that contain complex structures or consist of multiple nonlinear transformations. The calculation is applied in image recognition, speech recognition and other technologies. Taking the medical field as an example, deep learning will be used to process patients' diagnostic information to predict their condition and other conditions; under the requirements of morality and law, it is ne...

AI Technical Summary

Problems solved by technology

However, the inventor believes that the homomorphic encryption technology has certain limitations. The data encrypted by the homomorphic encryption algorithm is usually thousands of times larger than before; in addition, the operations supported by homomorphic encryption only support addition and multiplication, which is not yet mature. The scheme allows it to support operations such as comparison; and only multiplication is much more complicated than the multiplication of ordinary numbers, because in order to limit the growth of ciphertexts, it is necessary to perform reproducibility operations (RelinearizationOperation) after multiplication; therefore complex calculations and a large number of The combination of homomorphic encryption and deep learning is limited due to the occupation of storage resources

Images