Software security loophole prediction method based on assembly dependence diagram

A technology for software security and prediction methods, applied in computer security devices, instruments, electrical digital data processing, etc.

Active Publication Date: 2018-03-13
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Judging from the published literature, there is still a lot of room for performance improvement of the vulnerability prediction model

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
  • Software security loophole prediction method based on assembly dependence diagram
  • Software security loophole prediction method based on assembly dependence diagram
  • Software security loophole prediction method based on assembly dependence diagram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Taking the vulnerability prediction of the open source software project Firefox as an example, the vulnerability prediction process is given in detail below.

[0028] Step 1. Build the component dependency graph of the predicted software

[0029] A software system can be viewed as a collection of components and their relationships. The connection between components is actually the connection between the members in the components, so the relationship between components is determined by the relationship between the members in the components. From a static point of view, a component's members include executable code and data items. The relationship between executable code and data items includes data reading and data writing, and the relationship between executable code and executable code includes function calling and function returning.

[0030] A component is a triplet CC , M C , R C >, where D C is a collection of shared variables or data members, M C is a collec...

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 provides a software security loophole prediction method based on an assembly dependence diagram and provides a software code measuring index from different angles to establish a loopholeprediction model. The software security loophole prediction method comprises the following steps that 1, the assembly dependence diagram of prediction software is established; 2, network attribute values of nodes in the assembly dependence diagram in the step 1 are calculated; 3, all software loopholes of the prediction software are searched from a disclosed software loophole library, and a historical loophole library of the software is established; 4, network attribute values, calculated in the step 2, of the nodes serve as inputs of a machine learning algorithm, the number of loopholes in the step 3 serves as an output of the machine learning algorithm, the machine learning algorithm is trained and tested, and a prediction model having optimal performance is determined according to performance evaluation indexes of the machine learning algorithm; 5, the prediction model having optimal performance obtained in the step 4 is applied to loophole prediction of new software assemblies ofa software project.

Description

technical field [0001] The invention relates to a method for predicting software security vulnerabilities based on a component dependency graph, and belongs to the technical field of software quality assurance. Background technique [0002] At present, many literatures study the prediction of software security vulnerabilities, and establish a vulnerability prediction model (Vulnerability Prediction Model, VPM). The vulnerability prediction model uses machine learning algorithms to extract code metrics from software codes as features, and obtains indicator data from a large number of codes known to have vulnerabilities to train the model. The trained model can detect vulnerabilities in new codes. predict. The result of the prediction gives the probability that the module is vulnerable, or the number of modules that are vulnerable. The research ideas and methods of VPM mainly draw on the research ideas and methods of the software defect prediction model (Defect Prediction Mo...

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 Applications(China)
IPC IPC(8): G06F21/57
CPCG06F21/577G06F2221/033
Inventor 危胜军林婷单纯胡昌振何涛
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