Prior studies have demonstrated that deep learning-based approaches can enhance the performance of source code vulnerability detection by training neural networks to learn vulnerability patterns in code representation...Prior studies have demonstrated that deep learning-based approaches can enhance the performance of source code vulnerability detection by training neural networks to learn vulnerability patterns in code representations.However,due to limitations in code representation and neural network design,the validity and practicality of the model still need to be improved.Additionally,due to differences in programming languages,most methods lack cross-language detection generality.To address these issues,in this paper,we analyze the shortcomings of previous code representations and neural networks.We propose a novel hierarchical code representation that combines Concrete Syntax Trees(CST)with Program Dependence Graphs(PDG).Furthermore,we introduce a Tree-Graph-Gated-Attention(TGGA)network based on gated recurrent units and attention mechanisms to build a Hierarchical Code Representation learning-based Vulnerability Detection(HCRVD)system.This system enables cross-language vulnerability detection at the function-level.The experiments show that HCRVD surpasses many competitors in vulnerability detection capabilities.It benefits from the hierarchical code representation learning method,and outperforms baseline in cross-language vulnerability detection by 9.772%and 11.819%in the C/C++and Java datasets,respectively.Moreover,HCRVD has certain ability to detect vulnerabilities in unknown programming languages and is useful in real open-source projects.HCRVD shows good validity,generality and practicality.展开更多
针对现有的基于异构图神经网络的短文本分类方法未充分利用节点之间的有效信息,以及存在的过拟合问题,文中提出基于门控双层异构图注意力网络的半监督短文本分类方法(Semi-Supervised Short Text Classification with Gated Double-Laye...针对现有的基于异构图神经网络的短文本分类方法未充分利用节点之间的有效信息,以及存在的过拟合问题,文中提出基于门控双层异构图注意力网络的半监督短文本分类方法(Semi-Supervised Short Text Classification with Gated Double-Layer Heterogeneous Graph Attention Network,GDHG).GDHG包含节点注意力机制和门控异构图注意力网络两层.首先,使用节点注意力机制,训练不同类型的节点注意力系数,再将系数输入门控异构图注意力网络,训练得到门控双层注意力.然后,将门控双层注意力与节点的不同状态相乘,得到聚合的节点特征.最后,使用softmax函数对文本进行分类.GDHG利用节点注意力机制和门控异构图注意力网络的信息遗忘机制对节点信息进行聚集,得到有效的相邻节点信息,进而挖掘不同邻居节点的隐藏信息,提高聚合远程节点信息的能力.在Twitter、MR、Snippets、AGNews四个短文本数据集上的实验验证GDHG性能较优.展开更多
基金funded by the Major Science and Technology Projects in Henan Province,China,Grant No.221100210600.
文摘Prior studies have demonstrated that deep learning-based approaches can enhance the performance of source code vulnerability detection by training neural networks to learn vulnerability patterns in code representations.However,due to limitations in code representation and neural network design,the validity and practicality of the model still need to be improved.Additionally,due to differences in programming languages,most methods lack cross-language detection generality.To address these issues,in this paper,we analyze the shortcomings of previous code representations and neural networks.We propose a novel hierarchical code representation that combines Concrete Syntax Trees(CST)with Program Dependence Graphs(PDG).Furthermore,we introduce a Tree-Graph-Gated-Attention(TGGA)network based on gated recurrent units and attention mechanisms to build a Hierarchical Code Representation learning-based Vulnerability Detection(HCRVD)system.This system enables cross-language vulnerability detection at the function-level.The experiments show that HCRVD surpasses many competitors in vulnerability detection capabilities.It benefits from the hierarchical code representation learning method,and outperforms baseline in cross-language vulnerability detection by 9.772%and 11.819%in the C/C++and Java datasets,respectively.Moreover,HCRVD has certain ability to detect vulnerabilities in unknown programming languages and is useful in real open-source projects.HCRVD shows good validity,generality and practicality.
文摘针对现有的基于异构图神经网络的短文本分类方法未充分利用节点之间的有效信息,以及存在的过拟合问题,文中提出基于门控双层异构图注意力网络的半监督短文本分类方法(Semi-Supervised Short Text Classification with Gated Double-Layer Heterogeneous Graph Attention Network,GDHG).GDHG包含节点注意力机制和门控异构图注意力网络两层.首先,使用节点注意力机制,训练不同类型的节点注意力系数,再将系数输入门控异构图注意力网络,训练得到门控双层注意力.然后,将门控双层注意力与节点的不同状态相乘,得到聚合的节点特征.最后,使用softmax函数对文本进行分类.GDHG利用节点注意力机制和门控异构图注意力网络的信息遗忘机制对节点信息进行聚集,得到有效的相邻节点信息,进而挖掘不同邻居节点的隐藏信息,提高聚合远程节点信息的能力.在Twitter、MR、Snippets、AGNews四个短文本数据集上的实验验证GDHG性能较优.
