Minicursos Do XXI Simpósio Brasileiro De Segurança Da Informação E De Sistemas Computacionais 2021
DOI: 10.5753/sbc.7165.8.4
|View full text |Cite
|
Sign up to set email alerts
|

Segurança em Redes 5G: Oportunidades e Desafios em Detecção de Anomalias e Predição de Tráfego Baseadas em Aprendizado de Máquina

Abstract: This chapter focuses on approaching and contextualizing the security of the fifthgeneration (5G) mobile networks, discussing network anomaly detection techniques through hybrid tools. Classical techniques for prediction, such as time series regression analysis and the Hidden Markov Model, are revisited. New anomaly detection and traffic prediction techniques based on deep learning are presented, such as recurrent neural networks, neural networks with long short-term memory, and convolutional neural networks. F… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
1
0
1

Year Published

2024
2024
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 50 publications
(61 reference statements)
0
1
0
1
Order By: Relevance
“…The main function of the pooling layers is to simplify the information at the output of the convolutional layer [31], reducing the size of the data, as well as helping to make the representation constant in small translations of the input. The deep learning used with convolutional neural networks is characterized by the repetition of the convolutional and pooling layers [32]. Finally, the fully connected layer is responsible for propagating the signal through point-to-point multiplication and the use of an activation function.…”
Section: Cnn Architecturesmentioning
confidence: 99%
“…The main function of the pooling layers is to simplify the information at the output of the convolutional layer [31], reducing the size of the data, as well as helping to make the representation constant in small translations of the input. The deep learning used with convolutional neural networks is characterized by the repetition of the convolutional and pooling layers [32]. Finally, the fully connected layer is responsible for propagating the signal through point-to-point multiplication and the use of an activation function.…”
Section: Cnn Architecturesmentioning
confidence: 99%
“…Como em qualquer outra rede neural, uma rede LSTM pode ter várias camadas ocultas e, à medida que passa por todas as camadas, as informações relevantes são mantidas e todas as informações irrelevantes são descartadas em cada célula. As LSTMs são bem adequadas para modelagem de dados contínuos para tradução de idiomas, legendas em imagens e geração de textos, entre outras aplicações do PLN, por meio do reconhecimento de padrões (BARBOSA et al, 2021). Por fim, a tarefa de extrair informações úteis do estado da célula atual para serem apresentadas como uma saída é feita pelo portão OUTPUT.…”
Section: Lstmunclassified