mulsign / gnn-cfg

Model for Innovation project 'Static vulnerability detection based on control-flow-graph'

Model

基于控制流图的漏洞代码检测模型

Content

• path2data.py输入样本所在路径，生成对应的dataset
• train4.py 模型及主要训练函数
• word2vec.model全局w2v模型
• Digraph.gv.pdftorchviz自动生成的模型结构图
• sa_test4.py基于GCN的相似性检测（模板匹配）程序

Reference

Top-K Pooling from Gao and Ji: Graph U-Nets(ICML 2019), Cangea et al: Towards Sparse Hierarchical Graph Classifiers(NeurIPS-W 2018) and Knyazev et al.: Understanding Attention and Generalization in Graph Neural Networks (ICLR-W 2019)
Source Code:[Example]