LATIDIA · Ciberseguridad

E-UDE: Un modelo científico de aprendizaje automático para la dinámica de propagación del malware

arXiv:2611.00971v1 Anuncio Tipo: nuevo Resumen: Comprender la dinámica de propagación del malware en Internet es crucial para controlar eficazmente su propagación. Los modelos mecanicistas y basados ​​en datos existentes en el contexto

La noticia

arXiv:2611.00971v1 Announce Type: new Abstract: Understanding the malware propagation dynamics over the Internet is crucial for effectively controlling its spread. Existing mechanistic and data-driven models in the context of malware propagation dynamics, have some issues with either interpretability or predictive accuracy. This study presents an Enhanced Universal Differential Equation (E-UDE) framework that explicitly incorporates more detailed key factors that influence malware propagation. Evaluation on real-world malware propagation data shows that the E-UDE achieves the best overall performance, attaining an overall RMSE of 783.70 and MAE of 421.65. Compared with the Classical ODE and the UDE models, the proposed approach reduces RMSE by approximately 66 percent and 39 percent, respectively. Its