DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection.
Yizheng ChenZhoujie DingXinyun ChenDavid A. WagnerPublished in: CoRR (2023)
Keyphrases
- source code
- deep learning
- open source
- software systems
- software projects
- unsupervised learning
- unsupervised feature learning
- software maintenance
- machine learning
- high level
- software repositories
- plagiarism detection
- program understanding
- object detection
- software evolution
- text files
- weakly supervised
- domain specific
- software engineering
- data sets
- mental models
- object detectors
- image segmentation
- bug localization