Machine learning-based ransomware detection approaches

• Autores: Avila Reyes, Luis Fernando, Galvez Carrillo, Kevin Eduardo, Mendoza De Los Santos, Alberto Carlos
• Formato: artículo
• Fecha de Publicación: 2026
• Institución: Universidad La Salle
• Repositorio: Revistas - Universidad La Salle
• Lenguaje: español
• OAI Identifier: oai:ojs.revistas.ulasalle.edu.pe:article/342
• Enlace del recurso: https://revistas.ulasalle.edu.pe/innosoft/article/view/342; https://doi.org/10.48168/innosoft.s29.a342; https://n2t.net/ark:/42411/s29/a342
• Nivel de acceso: acceso abierto
• Materia: Machine learning; Cybersecurity; Detection; Ransomware; Neural networks; Aprendizaje automático; Ciberseguridad; Detección; Redes neuronales

The study aimed to analyze machine learning-based ransomware detection approaches in order to identify the most effective proposals reported in recent literature. The PRISMA methodology was applied to select original articles published between 2020 and 2025 in specialized databases. Findings show that traditional signature-based methods are insufficient against zero-day variants, while algorithms such as Random Forest, Gradient Boosting, and deep neural networks provide higher accuracy and adaptability. Likewise, hybrid and emerging approaches that incorporate forensic analysis with language models or explainable artificial intelligence stand out. It is concluded that machine learning techniques represent a robust and evolving alternative for early ransomware detection, contributing to strengthening the resilience of cybersecurity systems.