TCC - Bacharelado em Ciência da Computação (Sede)

URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/415

Navegar

Assunto: search.filters.subject.Segurança de computadores

Resultados da Pesquisa

Agora exibindo 1 - 3 de 3
  • Imagem de Miniatura
    Item
    Utilização de inteligência de ameaças cibernéticas para prevenção e mitigação de ataques ransomware: uma revisão sistemática da literatura
    (2025-02-27) Cabral, Rennan Luis Barros; Lins, Fernando Antonio Aires; http://lattes.cnpq.br/2475965771605110; http://lattes.cnpq.br/4612932794474682
  • Imagem de Miniatura
    Item
    Uma análise do impacto das linguagens de programação nos custos de execução no AWS Lambda em cenários de cold start e warm start
    (2023-04-24) Andrade Júnior, Edilson Alves de; Medeiros, Robson Wagner Albuquerque de; http://lattes.cnpq.br/3169193612606500; http://lattes.cnpq.br/5131828050788518
    Public cloud computing solutions have gained visibility on the market for offering great advantages over on-premises systems. However, cloud-based management workflows also brings concerns. As well as problems related to information security and lack of skilled professionals, cost management is one of the main challenges faced by users and organizations that migrate or already have their operations on cloud. Cloud providers define variables that directly affect cost behaviors, in addition, factors such as key characteristics of programming languages can also contribute to change those behaviors. This work aimed to understand how programming languages behave in cloud services such as AWS Lambda, so that cost management is carried out more assertively and efficiently, directly contributing to the reduction of costs and financial waste when using this kind of service. The results showed that the characteristics of programming languages significantly interfere in the financial costs of execution, elucidating that the choice of a certain programming language should be considered when cost is a requirement to be met when using AWS Lambda.
  • Imagem de Miniatura
    Item
    Aprendizado profundo com capacidade computacional reduzida: uma aplicação à quebra de CAPTCHAs
    (2018-08-16) Melo, Diogo Felipe Félix de; Sampaio, Pablo Azevedo; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/2213650736070295
    During the last decade, Deep Neural Networks has been shown to be a powerfull machine learn technique. Generally, to obtain relevant results, these techniques require high computacional power and large volumes of data, which can be a limiting factor on some cases. Neverthless, a careful project of trainig and archtecture may help to reduce these requirements. In the this work we present a comparative approach to the application of deep neural networks to text based CAPTCHAs as a way to cope with these limitations. We studied models that are capable of learn to segment and identify the text content of images, only based on examples. By experimentation of different hiper-parameters and architectures, we were capable to obtain a final model with 96.06% of token prediction accuracy in approximately 3 hours of training in a simple personal computer.