VISION is a framework for robust and interpretable code vulnerability detection using counterfactual data augmentation. It leverages GNNs, LLM-generated counterfactuals, and graph-based explainability to mitigate spurious correlations and improve generalization on real-world vulnerabilities (CWE-20).
spurious-correlations vulnerability-detection joern illuminati counterfactuals gnn-architectures augmentation-pipeline devign explainability-ai ai-robustness cwe-20
-
Updated
Oct 19, 2025 - Jupyter Notebook