Unlock instant, AI-driven research and patent intelligence for your innovation.

Method, device and equipment for training gbdt model in trusted execution environment

An execution environment and trusted technology, applied in the computer field, can solve problems such as data leakage and achieve the effect of ensuring security

Active Publication Date: 2022-03-01
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the process of training the GBDT model, there is a risk of data leakage

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device and equipment for training gbdt model in trusted execution environment
  • Method, device and equipment for training gbdt model in trusted execution environment
  • Method, device and equipment for training gbdt model in trusted execution environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The solutions provided in this specification will be described below in conjunction with the accompanying drawings.

[0034] Before describing the scheme provided by this specification, the inventive concept of this scheme is explained as follows.

[0035] In order to ensure the security of data during the model training process, the applicant of this application will execute the training process of the GBDT model in a trusted execution environment (Trusted Execution Environment, TEE). TEE is a powerful tool for secure computing, which can perform outsourced computing or multi-party secure computing in a secure domain. The two main features of TEE are isolation and verification: isolation ensures that data in the security domain cannot be accessed outside the security domain, and verification is used for users to confirm the security and integrity of the security domain and then negotiate secrets with the security domain.

[0036] At present, the more commonly used TEE...

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

No PUM Login to View More

Abstract

The embodiment of this specification provides a method, device and equipment for training a GBDT model in a trusted execution environment. In the training method, for the current node in the current decision tree, each feature in the D-dimensional feature is used as the current feature in turn. , to perform node split judgment on the current node. The node split judgment includes: loading N encrypted arrays of the current feature into the trusted memory area and decrypting. Each of the obtained N original arrays is used as the current array in turn, and based on the current eigenvalues ​​in the current array, the sample set corresponding to the current node is hypothetically divided, and based on the hypothetical segmentation results, the current optimal split of the current node is determined features and the current best feature threshold. After the node segmentation judgment is performed based on each feature in the D-dimensional feature, the sample set corresponding to the current node is segmented, and the child nodes corresponding to the current node are generated until the leaf node is reached. Thus, the safe training of GBDT model based on private data can be realized.

Description

technical field [0001] One or more embodiments of this specification relate to the field of computer technology, and in particular to a method, device and equipment for training a GBDT model in a trusted execution environment. Background technique [0002] In the context of the rapid development of Internet technology, data mining in the Internet has become more and more important. Usually, in data mining, machine learning is used to model based on calibration data, so that the trained model can be used to process the data to be predicted. Among various machine learning algorithms, the GBDT (Gradient boosting decision tree) algorithm is more and more widely used due to its excellent learning performance. The GBDT algorithm is a machine learning technique for regression, classification, sorting and other tasks. It obtains a strong prediction model by combining multiple weak learners (usually decision trees), also known as the GBDT model. [0003] However, in the process of ...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06N20/00
CPCG06N20/00
Inventor 赵原殷山
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD