Vulnerability Detection on Draper
60.7F1 ScoreWhite-Basilisk
Evaluation results
| Method | Links | |
|---|---|---|
| White-BasiliskTraining Strategy=Dataset-Specific2025.07 | 60.7 | |
| VulBERTa-CNN2025.07 | 57.9 | |
| Russell et al. (2018)2025.07 | 56.6 | |
| White-BasiliskTraining Strategy=Unified2025.07 | 54.9 | |
| Baseline-TextCNN2025.07 | 49.4 | |
| Baseline-BiLSTM2025.07 | 46.8 | |
| VulBERTa-MLP2025.07 | 43.3 |