Implementación de Modelos de Aprendizaje Supervisado para la Detección de Tráfico Malicioso

Miguel Alfonso  Negrete Romero; José Francisco  Ortiz Morales; Jorge  Gómez Gómez

no title

Authors

Miguel Alfonso Negrete Romero Author
José Francisco Ortiz Morales Author
Jorge Gómez Gómez Universidad de Córdoba Author

Keywords:

Artificial intelligence, malware, machine learning, Machine learning models, Intrusion Detection System, supervised learning

Abstract

The increasing interconnectedness of devices and sys
tems has heightened cyber threats and malicious traffic,
prompting the development of Artificial Intelligence-based
algorithms for detection. This study investigates advanced
Machine Learning methods to enhance security, focusing on
the effectiveness of different models in detecting threats
such as Denial of Service attacks and intrusions. Datasets
like KDD Cup 99 and Network Traffic Data-Malicious Activity
Detection are used to experiment with various algorithms.
Detailed data analysis and algorithm evaluation highlight
the viability of these techniques to strengthen cybersecurity.