Text deep learning-based software security vulnerability prediction method

A deep learning and software security technology, applied in computer security devices, special data processing applications, instruments, etc., can solve the problems of insufficient vulnerability prediction effect and poor feature learning effect, and achieve high accuracy, false alarm rate and missed alarm rate. The effect of low and improved performance indicators

Pending Publication Date: 2018-09-18
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this case, the machine learning algorithm based on shallow learning, which is often used at present, has poor feat

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
  • Text deep learning-based software security vulnerability prediction method
  • Text deep learning-based software security vulnerability prediction method
  • Text deep learning-based software security vulnerability prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings.

[0032] Such as figure 2 As shown, the software security vulnerability prediction method based on text deep learning of the present invention comprises the following steps:

[0033] Step 1, software source code text word feature extraction

[0034] For the source code of a software project (that is, the prediction object), take the software module in it as the processing unit, first remove the punctuation marks and code comments that appear in the module source code text, and use spaces as separators for the remaining text Extract each word, and count the number of occurrences of each word in the entire text, and finally normalize the number of occurrences. The result of the processing is the frequency of occurrence of the word, thus obtaining the source code text for this module. The eigenvectors, set to the following representation:

[0035] ComponentName: (Item_1...

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 invention discloses a text deep learning-based software security vulnerability prediction method, which learns features and knowledge from a historical software source code text by adopting a deepneural network model and a shallow machine learning algorithm, and can be used for predicting security vulnerabilities in new software source codes. According to the method, structural features in the features of the software source code text are learnt by adopting the deep neural network model; by taking the learnt features as inputs of a classifier, the classifier is subjected to training adjustment; an optimal vulnerability prediction model is obtained; and the method is used for vulnerability prediction of new software modules of software.

Description

technical field [0001] The invention relates to a software security loophole prediction method based on text deep learning, and belongs to the technical field of software security loophole prediction. Background technique [0002] Software security vulnerability prediction can know in advance the possibility or quantity of software vulnerabilities in software source code modules. According to the prediction results, software developers can invest limited time and funds in targeted projects with high probability and large number of vulnerabilities. In the testing of software modules, the efficiency of software testing can be improved. [0003] At present, commonly used software vulnerability prediction uses shallow machine learning methods to establish software vulnerability prediction models. The establishment process is as follows: figure 1 Shown: [0004] ① Establishment of metrics for software source code modules [0005] At present, there are mainly two methods for es...

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
IPC IPC(8): G06F21/57G06F17/30G06F17/27
CPCG06F21/577G06F2221/033G06F40/284
Inventor 危胜军钟浩单纯胡昌振牛中盈
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap