LLM-generated counterfactual code pairs with flipped vulnerability labels, used to train a GNN, sharply improve CWE-20 detection and attribution on the released CWE-20-CFA benchmark.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation
LLM-generated counterfactual code pairs with flipped vulnerability labels, used to train a GNN, sharply improve CWE-20 detection and attribution on the released CWE-20-CFA benchmark.