MVD: Memory-Related Vulnerability Detection Based on Flow-Sensitive Graph Neural Networks
Abstract
Memory-related vulnerabilities constitute severe threats to the security of modern software. Despite the success of deep learning-based approaches to generic vulnerability detection, they are still limited by the underutilization of flow information when applied for detecting memory-related vulnerabilities, leading to high false positives.
BibTeX
@inproceedings{Cao-al:ICSE22,
author = {Sicong Cao and
Xiaobing Sun and
Lili Bo and
Rongxin Wu and
Bin Li and
Chuanqi Tao},
title = {{MVD:} {Memory-Related} Vulnerability Detection Based on {Flow-Sensitive} Graph Neural Networks},
booktitle = {ICSE},
pages = {1456--1468},
publisher = {{ACM}},
year = {2022},
}