LATIDIA · Ciberseguridad

Del laboratorio a la realidad: una evaluación práctica de modelos de aprendizaje profundo y LLM para la detección de vulnerabilidades

arXiv: 2512.10485v4Tipo de anuncio: reemplazar Resumen: Los métodos de detección de vulnerabilidades basados en el aprendizaje profundo (DL) han demostrado un gran rendimiento en los conjuntos de datos de referencia, pero su efectividad en el mundo real sigue siendo subexplorada

La noticia

arXiv:2512.10485v4 Announce Type: replace Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored. Recent work suggests that graph neural network-based and transformer-based models, including large language models (LLMs), yield promising results when evaluated on curated benchmark datasets. These datasets are typically characterized by similar data distributions and may contain synthetic samples, heuristic labels, or labeling noise. In this study, we systematically evaluate four representative DL models---Devign, ReVeal, LineVul, and VulBERTa---across four representative datasets: Juliet, Devign, BigVul, and ICVul. Each model is trained independently on each dataset, and the graph-based and CodeBERT representations adopted by these models are