Leveraging User-Defined Identifiers for Counterfactual Data Generation in Source Code Vulnerability Detection.
Hongyu KuangFeng YangLong ZhangGaigai TangLin YangPublished in: SCAM (2023)
Keyphrases
- source code
- user defined
- data generation
- open source
- software systems
- data types
- software maintenance
- software projects
- plagiarism detection
- query language
- high level
- data streams
- software repositories
- database systems
- streaming data
- active learning
- real world
- software evolution
- free software
- anomaly detection
- data model
- source files
- bug localization
- program understanding
- software artifacts
- change detection
- feature space
- case study