Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data Augmentation

arXiv:2404.09599v1 Announce Type: new
Abstract: Source code vulnerability detection aims to identify inherent vulnerabilities to safeguard software systems from potential attacks. Many prior studies overlook diverse vulnerability characteristics, simplifying the problem into a binary (0-1) classification task for example determining whether it is vulnerable or not. This poses a challenge for a single deep learning-based model to effectively learn the wide array of vulnerability characteristics. Furthermore, due to the challenges associated with collecting large-scale vulnerability data, these detectors often overfit …

arxiv attacks augmentation binary challenge classification code code vulnerability cs.cr data detection identify problem safeguard software software systems source code studies systems task vulnerabilities vulnerability vulnerability detection vulnerable