Across six programming languages, fine-tuned language models detect JavaScript vulnerabilities with F1 scores near 70%, much higher than the low scores reported for C/C++, while code complexity metrics show no consistent relationship with detection performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vulnerability Detection in Popular Programming Languages with Language Models
Across six programming languages, fine-tuned language models detect JavaScript vulnerabilities with F1 scores near 70%, much higher than the low scores reported for C/C++, while code complexity metrics show no consistent relationship with detection performance.