VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs
Open paper
Benchmark
Model
Rank
Results
vulnerability-detection-on-vulscriber
Reveal Model - Tested on Reveal (Training on Devign + VulScribeR 20K + Extra Cleans)
#1
F1 Score: 26.18
Rank counts only results with a code link.