Evaluation of the performance of supervised and unsupervised Machine learning techniques for intrusion detection

Fernando Gutierrez Portela, Florina Almenares Mendoza, Liliana Calderon Benavides

Resultado de la investigación: Libro / Capitulo del libro / InformeLibros de Investigaciónrevisión exhaustiva

5 Citas (Scopus)

Resumen

machine learning techniques are widely used in the research for intelligent solutions anomalies detection on different computers and communications systems, which have allowed to modernize the intrusion detection systems, to ensure data privacy. For that, this paper evaluates the performance of some supervised (i.e., KNN and SVM) and unsupervised (i.e., Isolation Forest and K-Means) algorithms, for intrusion detection, using data set UNSW-NB12. The results show that the supervised algorithm SVM gaussiana fine, obtained 92% in accuracy, indicating the ability to correctly classify normal and abnormal data. With regard to the unsupervised algorithms, the K-Means algorithm groups the data together correctly and allows the appropriate number of groups to be clearly defined; however, this data set is highly agglomerated. For Isolation Forest, despite being a robust algorithm for the separation of atypical values, it presented difficulty for it. Finally, it should be made clear that not all methods of detecting anomalies by distance work properly for all data sets.

Idioma originalInglés
Título de la publicación alojada2019 IEEE International Conference on Applied Science and Advanced Technology, iCASAT 2019
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)9781728131108
DOI
EstadoPublicada - nov. 2019
Evento2019 IEEE International Conference on Applied Science and Advanced Technology, iCASAT 2019 - Queretaro, México
Duración: 27 nov. 201928 nov. 2019

Serie de la publicación

Nombre2019 IEEE International Conference on Applied Science and Advanced Technology, iCASAT 2019

Conferencia

Conferencia2019 IEEE International Conference on Applied Science and Advanced Technology, iCASAT 2019
País/TerritorioMéxico
CiudadQueretaro
Período27/11/1928/11/19

Huella

Profundice en los temas de investigación de 'Evaluation of the performance of supervised and unsupervised Machine learning techniques for intrusion detection'. En conjunto forman una huella única.

Citar esto