Manile Srun

From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python

Muntasir Adnan, Manile Srun, Carlos C. N. Kuhn

The original ALPHA benchmark introduced a taxonomy-aware penalty for evaluating CWE-level vulnerability prediction in Python and proposed that the penalty could theoretically also serve as a training signal. This paper provides that validation. We compare three delivery mechanism…Read more