Multi-party Privacy Preserving Machine Learning Method Based on Homomorphic Encryption and Trusted Hardware
A machine learning and homomorphic encryption technology, applied in the field of multi-party privacy protection machine learning, can solve the problems of accuracy loss, low efficiency of machine learning modeling, etc., and achieve the effect of low computing cost
Active Publication Date: 2021-12-31
HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0009] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, provide a multi-party privacy protection machine learning method based on homomorphic encryption and trusted hardware, and solve the problems caused by the use of homomorphic encryption technology by introducing trusted hardware. The problem of low efficiency and loss of accuracy in learning modeling
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0055] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Apparently, the described embodiments are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of this application.
[0056] Reference in this application to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a multi-party privacy protection machine learning method based on homomorphic encryption and trusted hardware, including: sk Send to each data party and trusted hardware R ;server S Integrate the ciphertext data uploaded by each data party to obtain the ciphertext data set; the server S On the basis of the ciphertext data set, the linear operation in the common machine learning algorithm is replaced by homomorphic addition and homomorphic multiplication, and machine learning modeling is performed in the ciphertext state; the server S After completing the machine learning modeling under the ciphertext, the encrypted model ciphertext is sent to each data party; each data party uses the private key to decrypt the model ciphertext, and obtains the data of each data party. D The trained model. The present invention utilizes the property of fully homomorphic encryption and relies on trusted hardware to simulate bootstrapping and execute activation functions, and can obtain an accuracy rate consistent with that of a model that performs machine learning training on unencrypted data.
Description
technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to a multi-party privacy protection machine learning method based on homomorphic encryption and trusted hardware. Background technique [0002] In recent years, with the surge in the amount of user data in various industries, more and more companies tend to use machine learning algorithms to build models to obtain more revenue and provide better services for users. However, using user data for machine learning modeling faces two important problems: 1. Due to the huge amount of data, it is necessary to use powerful cloud services for machine learning modeling, and directly uploading local user data to the server must It will lead to the leakage of user data privacy; 2. With the continuous deepening of the division of labor among industries, enterprises, and departments, complete user data is often scattered among different companies in the same industry and diffe...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F21/60G06N20/00H04L9/00
CPCG06F21/602G06N20/00H04L9/008H04L63/0442H04L2209/127H04L2209/46H04L63/0464
Inventor 蒋琳刘成金赵鑫王轩刘洋廖清漆舒汉张加佳吴宇琳陈倩
Owner HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)