Detecção de ataques cibernéticos utilizando aprendizado de máquina: uma revisão

Main Article Content

Ricardo da Silveira Lopes
Julio Cesar Duarte
Ronaldo Ribeiro Goldschmidt

Abstract

With the public availability of simulated intrusion detection datasets, Machine Learning has been increasingly used in cyber attack detection work. Despite the fact that the performance (precision and recall) has been highlighted, on the other hand, there has been a lack of critical analysis of what was actually learned by the model, with the intention to conclude whether or not this performance will be maintained in real applications. In this sense, explainability techniques appear as a promising possibility in the execution of this task, since the analysis of the False Positive Rate of these models has usually been neglected. This can become an important problem, with the increase in speed and amount of data transmitted over the internet. This research proposes to raise discussions about these problems, presenting some articles related to them.

Downloads

Download data is not yet available.

Article Details

How to Cite
Lopes, R. da S., Duarte, J. C., & Goldschmidt, R. R. (2022). Detecção de ataques cibernéticos utilizando aprendizado de máquina: uma revisão. Revista Militar De Ciência E Tecnologia, 39(2). Retrieved from http://www.ebrevistas.eb.mil.br/CT/article/view/10831
Section
Artigos
Author Biographies

Ricardo da Silveira Lopes, Instituto Militar de Engenharia

Ricardo da Silveira Lopes, Defense Engineering Section, Instituto Militar de Engenharia - Urca, Rio de Janeiro - RJ, Brazil Received the B.Sc. and M.Sc. degrees in 2007 and 2014, respectively, from the Military Institute of Engineering, Brazil, where he is currently pursuing the D.Sc. degree in Defense Engineering. His research interests include machine learning intrusion detection and explainable artificial intelligence.

Julio Cesar Duarte, Instituto Militar de Engenharia

Julio Cesar Duarte, Computer Engineering Teaching Section, Instituto Militar de Engenharia - Urca, Rio de Janeiro - RJ, Brazil Graduated from the Military Institute of Engineering (1998), Master's in Computer Science from the Pontifical Catholic University of Rio de Janeiro (2003) and PhD in Computer Science from the Pontifical Catholic University of Rio de Janeiro (2009). He has multidisciplinary experience, working on the following topics: machine learning, artificial intelligence and natural language processing.

Ronaldo Ribeiro Goldschmidt, Instituto Militar de Engenharia

Ronaldo Ribeiro Goldschmidt, Computer Engineering Teaching Section, Instituto Militar de Engenharia - Urca, Rio de Janeiro - RJ, Brazil Received the B.Sc. in Mathematics from Fluminense Federal University (1990), the M.Sc. in Computer Systems from the Military Institute of Engineering (1992) and the D.Sc. in Electrical Engineering from the Pontifical Catholic University of Rio de Janeiro (2004). He currently works as an associate professor at the Military Institute of Engineering and his research interests include Data Science and Artificial Intelligence.