MARGIN uses von Mises-Fisher concentration to dynamically adjust geometric regularization, aligning embedding distributions with Voronoi cells for more stable decision boundaries in imbalanced vulnerability detection.
An investigation of quality issues in vulnerability detection datasets
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
support 1representative citing papers
A systematic literature review categorizing 32 papers on threat and attack modelling for CPS and noting that current models fail to address dynamic, multi-layer, multi-path, and multi-agent attack characteristics.
citing papers explorer
-
MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection
MARGIN uses von Mises-Fisher concentration to dynamically adjust geometric regularization, aligning embedding distributions with Voronoi cells for more stable decision boundaries in imbalanced vulnerability detection.
-
Security Modelling for Cyber-Physical Systems: A Systematic Literature Review
A systematic literature review categorizing 32 papers on threat and attack modelling for CPS and noting that current models fail to address dynamic, multi-layer, multi-path, and multi-agent attack characteristics.