@inproceedings{58698e615f784633945d9acf605f0735,
title = "VinJ: An Automated Tool for Large-Scale Software Vulnerability Data Generation",
abstract = "We present VinJ, an efficient automated tool for large-scale diverse vulnerability data generation. VinJ automatically generates vulnerability data by injecting vulnerabilities into given programs, based on knowledge learned from existing vulnerability data. VinJ is able to generate diverse vulnerability data covering 18 CWEs with 69\% success rate and generate 686k vulnerability samples in 74 hours (i.e., 0.4 seconds per sample), indicating it is efficient. The generated data is able to improve existing DL-based vulnerability detection, localization, and repair models significantly. The demo video of VinJ can be found at https://youtu.be/-oKoUqBbxD4. The tool website can be found at https://github.com/NewGillig/VInj. We also release the generated large-scale vulnerability dataset, which can be found at https://zenodo.org/records/10574446.",
keywords = "Vulnerability analysis, data augmentation, deep learning",
author = "Yu Nong and Haoran Yang and Feng Chen and Haipeng Cai",
note = "Publisher Copyright: {\textcopyright} 2024 Copyright held by the owner/author(s).; 32nd ACM International Conference on the Foundations of Software Engineering, FSE Companion ; Conference date: 15-07-2024 Through 19-07-2024",
year = "2024",
month = jul,
day = "10",
doi = "10.1145/3663529.3663800",
language = "English",
series = "FSE Companion - Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering",
publisher = "Association for Computing Machinery, Inc",
pages = "567--571",
editor = "Marcelo d�Amorim",
booktitle = "FSE Companion - Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering",
}