Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

Predicción de ciberataques mediante el empleo de algoritmos deep learning

Authors: Gutiérrez Galeano, Leopoldo Jesús;

Predicción de ciberataques mediante el empleo de algoritmos deep learning

Abstract

La seguridad informática es un área muy necesaria debido a los nuevos tipos de ciberamenazas que aparecen continuamente. Para intentar minimizar al máximo posible los riesgos de ciberataques, es necesario el uso de herramientas y técnicas que sean capaces de detectarlas. Para ello, se entrena un modelo de detección de ciberataques, basado en algoritmos de aprendizaje profundo. Se ha seleccionado el modelo T5, pre-entrenado para tareas de procesamiento de lenguaje natural. Para los experimentos se ha utilizado el conjunto de datos CIC-IDS2017. Este dataset ha sido previamente limpiado y adaptado al modelo seleccionado, y se ha llevado a cabo un proceso de fine-tuning, a partir del cual se han conseguido unos resultados bastante buenos, superando el 97% de tasa de acierto, para el tamaño pre-entrenado más pequeño, t5-small, y más de un 99% para el segundo tamaño pre-entrenado más pequeño, t5-base. Finalmente se hace un estudio comparativo en relación a la evolución de las tasas de pérdida y las tasas de acierto, calculadas para cada tamaño y época. Por motivos de simplicidad se ha utilizado el wrapper SimpleT5, el cual permite utilizar el modelo T5 con pocas líneas de código.

Country
Spain
Related Organizations
Keywords

ciberataques, deep learning, detección, fine-tuning, T5

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green