AI RESEARCH
MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection
arXiv CS.LG
•
ArXi:2605.10240v1 Announce Type: cross Software vulnerability detection is critical for ensuring software security and reliability. Despite recent advances in deep learning, real-world vulnerability datasets suffer from two severe challenges: frequency imbalance and difficulty imbalance. We reinterpret these challenges from an embedding geometry perspective, observing that such imbalances induce geometric distortions in hyperspherical representation space.