Code plagiarism detection based on graph neural network
As open-source data becomes increasingly accessible,the cost of code plagiarism has de-creased,significantly impacting the healthy development of the software industry.Addressing the limi-tation of existing plagiarism detection methods,which struggle to deeply mine the semantic and struc-tural information of source code,leading to suboptimal semantic plagiarism detection results,this paper introduces a graph neural network-based code plagiarism detection method.This method uses graph neural networks to effectively represent the characteristics of source code,including semantic and struc-tural information,and employs graph attention networks to enhance these features.Furthermore,it utilizes neural tensor networks to obtain similarity vectors between different source codes.Finally,a fully connected network calculates the similarity between different source codes.Meanwhile,the drop-out mechanism is incorporated to balance neuron weights,optimize model design,and prevent overfit-ting.To validate the effectiveness of the proposed method,experiments were conducted on an OJ sys-tem dataset,and the results were compared with those of current popular detection methods.The ex-perimental results demonstrate that the proposed method achieves better performance.
code plagiarism detectiondeep semantic and structural information extractiongraph neural networkgraph attention networkfeature enhancement
万方数据
维普
