Software defect detection model establishment and detection method and system based on Github

Abstract

The invention discloses a software defect detection model establishment and detection method and system based on Github, and the method comprises the steps: firstly carrying out the preprocessing of adata set in a Github platform, and obtaining a change record meeting the requirements and a Bug-Fix file pair corresponding to the change record; processing the change records meeting the requirements to generate vectors and labels of the slices; and finally, inputting the vector and the label of the slice into a bidirectional LSTM model for training and learning to obtain a trained detection model. And for a to-be-detected target file, processing the to-be-detected target file to obtain a vector of the target file, and inputting the vector into the detection model to obtain a detection result. The method provided by the invention solves the problems of data imbalance, insufficient data diversity and poor model generalization ability which must be faced by a too small data set in currentdefect detection based on source code learning; and higher detection accuracy can be achieved.

Description

technical field [0001] The invention belongs to the technical field of code auditing, and in particular relates to a Github-based software defect detection model establishment, detection method and system. Background technique [0002] A variety of defect analysis tools already exist in the field of code auditing, which attempt to detect common defects in software. Static detection tools such as Clang can do this without executing the program. Dynamic inspection tools detect defects by repeatedly executing many test cases on real or virtual processors. Both static and dynamic detection tools are based on manual definition of defect rules, so they are limited to manual design rules and cannot guarantee complete testing of the code base. Symbolic execution replaces input data with symbolic values, and performs analysis and diagnosis on the control flow diagram of the program. Although it can probe all feasible program paths, symbolic execution is expensive and does not scal...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the deficiencies in the prior art, the present invention provides a Github-based software defect detection model establishment, detection method and system to solve the existing method loopholes The library is updated slowly, there are few types of defects, and the defect coverage rate is low. As a result, the defect static detection technology must face the problems of sample imbalance, the model cannot be used to detect complex and diverse defects, and the model fails quickly.

Images