Improved Labeling of Security Defects in Code Review by Active Learning with LLMs
Mining high-quality datasets of security defects is important for cybersecurity. In this paper, we focus on mining a dataset of reviews that discuss potential security defects in code or other artifacts. Mining such datasets often involves labeling, and this is challenging because security defects are rare.
Authors
- Johannes Härtel (ORCID: https://orcid.org/0000-0002-7461-2320)
Institutions
- Vrije Universiteit Amsterdam (NL)
Publication Details
- Published
- 2025-06-17
- DOI
- https://doi.org/10.1145/3756681.3756986
- Primary Topic
- Software Engineering Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00