| Title | Graph Neural Network-based Vulnerability Predication |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Feng, Qi, Feng, Chendong, Hong, Weijiang |
| Conference Name | 2020 IEEE International Conference on Software Maintenance and Evolution (ICSME) |
| Date Published | sep |
| Keywords | AST, Benchmark testing, CFG, compositionality, Conferences, CPG, encoding, GNN, Human Behavior, Learning systems, Metrics, pubcrawl, Resiliency, software maintenance, vulnerability detection, vulnerability predication |
| Abstract | Automatic vulnerability detection is challenging. In this paper, we report our in-progress work of vulnerability prediction based on graph neural network (GNN). We propose a general GNN-based framework for predicting the vulnerabilities in program functions. We study the different instantiations of the framework in representative program graph representations, initial node encodings, and GNN learning methods. The preliminary experimental results on a representative benchmark indicate that the GNN-based method can improve the accuracy and recall rates of vulnerability prediction. |
| DOI | 10.1109/ICSME46990.2020.00096 |
| Citation Key | feng_graph_2020 |
Graph Neural Network-based Vulnerability Predication