Predicting buffer overflow using semi-supervised learning
Predicting buffer overflow using semi-supervised learning
复制标题
使用半监督学习预测缓冲区溢出
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Chaojing Tang
中科院分区：
文献类型：
--
作者：
Qingkun Meng;Shameng Wen;Chao Feng;Chaojing Tang
众所周知，漏洞检测是一项非常困难和耗时的工作，因此充分利用未标记的数据是必要的，也是有益的。针对这一现实，本文提出了一种基于半监督学习的缓冲区溢出预测方法。我们首先使用Antlr从C/C++源文件中提取AST，然后根据22个缓冲区溢出属性分类，从AST中的每个函数提取一个22维向量，最后利用该向量训练分类器来预测缓冲区溢出漏洞。实验和评价表明，该方法是正确和有效的。
As everyone knows vulnerability detection is a very difficult and time consuming work, so taking advantage of the unlabeled data sufficiently is needed and helpful. According the above reality, in this paper a method is proposed to predict buffer overflow based on semi-supervised learning. We first employ Antlr to extract AST from C/C++ source files, then according to the 22 buffer overflow attributes taxonomies, a 22-dimension vector is extracted from every function in AST, at last, the vector is leveraged to train a classifier to predict buffer overflow vulnerabilities. The experiment and evaluation indicate our method is correct and efficient.