WeSCE Benchmark
Explore score history ↗WeSCE is a benchmark for quantifying security drift in LLM-driven code editing. It consists of 400 executable programs derived from real-world code, covering feature addition, removal, bug fixing, and refactoring. The benchmark proposes a continuous risk representation and drift measures that capture changes in overall risk, worst-case severity, and vulnerability distribution.
- Released
- 2026-08-15
- Institutions
- Zhejiang University
- Evaluates
- Cybersecurity, Language & Knowledge, cs.CR
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
WeSCE paper
No reported scores are on record for this benchmark yet.