Source code multi-tag graph neural network-based program code copying type detection method and system

Abstract

The invention relates to a source code multi-tag graph neural network-based program code copying type detection method. The method comprises the following steps of S1, for a code text, generating a copying version by utilizing a self-defined code micro-confusion tool, and recording a copying type; S2, performing code attribute graph eigenvector extraction on the code text and the copying version;S3, integrating code attribute graph eigenvectors of the code text and the copying version, providing a good input for a neural network, and setting integrated code attribute graph eigenvectors of thecode text and the copying version as positive examples; S4, performing integration by utilizing the methods in the steps S2-S3 to obtain code attribute graph eigenvectors of the code text-the code text, and setting the code attribute graph eigenvectors of the code text-the code text as negative examples; and S5, defining a multi-task learning network model by utilizing the neural network, training 10 classifiers at the same time for each positive example / negative example, and finally outputting a 10-dimension vector, thereby providing a copying evidence for an assessor, wherein each dimensionrepresents a defined copying type.

Description

technical field [0001] The invention relates to the field of code plagiarism detection, and more specifically, to a method and system for detecting program code plagiarism types based on a source code multi-label graph neural network. Background technique [0002] Program code plagiarism means that the plagiarist's program code is obtained by directly copying other people's source code or by slightly modifying other people's source code; code plagiarism detection refers to extracting code feature strings or fingerprints, and then using a certain matching algorithm To calculate the similarity of two codes, plagiarism forensics refers to the process of plagiarism detection, recording the possibility of a certain method of plagiarism, as a reference for suspected plagiarism. With the continuous development of information technology, the practicability and necessity of program code plagiarism detection in some specific occasions has become increasingly significant, especially in...

AI Technical Summary

Problems solved by technology

The program code has strong structural characteristics, and the detection of a single technology can only target one or two kinds of plagiarism methods, and each type of technology has its own technical characteristics and advantages and disadvantages. There are different performances in terms of space-time complexity and other aspects. The more plagiarism means that can be detected means that more structural information is considered, which leads to the more complex intermediate representation of the input code.

[0019] Another reason is that judging whether there is plagiarism in the two codes itself is quite subjective.

Images