FuncVul fine-tunes GraphCodeBERT on three-line code chunks around patches, labeled with LLM assistance, reaching 87-92% accuracy and F1 on six datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FuncVul: An Effective Function Level Vulnerability Detection Model using LLM and Code Chunk
FuncVul fine-tunes GraphCodeBERT on three-line code chunks around patches, labeled with LLM assistance, reaching 87-92% accuracy and F1 on six datasets.