Ítem
Acceso Abierto
Detección de anomalías en tráfico de red de Sistemas de Control Industrial soportada en algoritmos de machine learning
Título de la revista
Autores
Tristancho Muñoz, Miguel Angel
Archivos
Fecha
2023-02-07
Directores
Díaz López, Daniel Orlando
ISSN de la revista
Título del volumen
Editor
Universidad del Rosario
Buscar en:
Métricas alternativas
Resumen
Establecer un sistema de análisis de tráfico de red basado en algoritmos de machine learning (ML), orientado a sistemas de control industrial que permita: la identificación de comportamientos anormales para evitar la explotación de vulnerabilidades que afecten la seguridad de procesos industriales reduciendo riesgos de disponibilidad y soporte la continuidad del negocio.
Abstract
The growing development of computer networks associated with industrial systems and their integration with corporate networks (Internet) have made this group a desired target for cybercriminals worldwide. Mitigating this type of risk is one of the highest priorities for integrators, manufacturers, and users of control systems due to the great impact that can occur on the economy, the environment and the people in an organization when materialization occurs. of an attempted attack or sabotage of industrial processes. It is becoming increasingly important for industrial organizations to become aware of the weakness of these systems and seek organizational structures for security management that help them optimize their protection against external threats from all points of view to detect and address incidents. security-related issues before they become a major problem.
Palabras clave
Machine learning , Sistemas de control industrial ICS , Tráfico de red industrial , Detección de anomalías , Reducción de riesgos en seguridad de procesos industriales
Keywords
Machine Learning , Cibersecurity
