本篇论文题目为：Explaining Graph Neural Networks for Vulnerability Discovery
发表于CCS 2021
本文主要内容是介绍GNNs->前人对GNNs的应用与改进->提出一种对GNNs的评估解释
本文并未实际构建一种方法去进行漏洞挖掘，而侧重于对GNNs在漏洞挖掘中的应用
针对应用文献进行梳理：
漏洞挖掘常规方法：
- 白盒方法：CAM（Wenjie Yang, Houjing Huang, Zhang Zhang, Xiaotang Chen, Kaiqi Huang, and Shu Zhang. 2019. Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification. (2019), 1389–1398. https://doi.org/ 10.1109/CVPR.2019.00148 ）和综合梯度法（Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic Attribution for Deep Networks. arXiv:1703.01365 [cs.LG]）
- 黑盒技术（CAM和综合梯度法已经被证明优于黑盒技术）：Alexander Warnecke, Daniel Arp, Christian Wressnegger, and Konrad Rieck. 2020. Evaluating Explanation Methods for Deep Learning in Security. In 2020 IEEE European Symposium on Security and Privacy (EuroS&P). IEEE, Genoa, Italy, 158–174. https://doi.org/10.1109/EuroSP48549.2020.00018
漏洞挖掘特定于图的方法（专门为提供GNN见解而设计）：
- GNNExplainer：Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019.
GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks. CoRR abs/1903.03894 (2019). arXiv:1903.03894 http://arxiv.org/abs/1903.03894
- PGExplainer：Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen,
and Xiang Zhang. 2020. Parameterized Explainer for Graph Neural Network. arXiv:2011.04573 [cs.LG]
- Graph-LRP：Thomas Schnake, Oliver Eberle, Jonas Lederer,Shinichi Nakajima, Kristof T.
Schütt, Klaus-Robert Müller, and Grégoire Montavon. 2020. Higher-Order Expla[1]nations of Graph Neural Networks via Relevant Walks. arXiv:2006.03589 [cs.LG]
用于漏洞挖掘的代码图和组合图：
- 程序依赖图（PDG）：Jeanne Ferrante, Karl J. Ottenstein, and Joe D. Warren. 1987. The Program Dependence Graph and Its Use in Optimization. ACM Trans. Program. Lang. Syst. 9, 3 (July 1987), 319–349. https://doi.org/10.1145/24039.24041
- 代码特性图（CPG）：
F. Yamaguchi, N. Golde, D. Arp, and K. Rieck. 2014. Modeling and Discovering
Vulnerabilities with Code Property Graphs. In 2014 IEEE Symposium on Security
and Privacy. 590–604. https://doi.org/10.1109/SP.2014.44
- 代码合成图（CCG）：
Sicong Cao, Xiaobing Sun, Lili Bo, Ying Wei, and Bin Li. 2021. BGNN4VD:
Constructing Bidirectional Graph Neural-Network for Vulnerability Detection.
Information and Software Technology 136 (2021), 106576. https://doi.org/10.1016/
j.infsof.2021.106576
除此之外，其余应用文献中有对GNN的改进以及对机器学习的改进等等。
标签：Explaining,doi,Neural,Graph,https,org,Networks From： https://blog.csdn.net/XLYcmy/article/details/144940472