Skip navigation
Use este identificador para citar ou linkar para este item: http://repositorio.unb.br/handle/10482/42130
Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
ARTIGO_FeatureEngineeringTopics.pdf6,96 MBAdobe PDFVisualizar/Abrir
Registro completo de metadados
Campo DCValorIdioma
dc.contributor.authorGualberto, Éder Souza-
dc.contributor.authorSouza Júnior, Rafael Timóteo de-
dc.contributor.authorVieira, Thiago Pereira de Brito-
dc.contributor.authorCosta, João Paulo Carvalho Lustosa da-
dc.contributor.authorDuque, Cláudio Gottschalg-
dc.date.accessioned2021-10-13T13:55:47Z-
dc.date.available2021-10-13T13:55:47Z-
dc.date.issued2021-04-21-
dc.identifier.citationGUALBERTO, Eder S. et al. From feature engineering and topics models to enhanced prediction rates in phishing detection. IEEE Access, v. 8, p. 76368-76385, 2021. DOI: 10.1109/ACCESS.2020.2989126. Disponível em: https://ieeexplore.ieee.org/abstract/document/9075252. Acesso em: 13 out. 2021.pt_BR
dc.identifier.urihttps://repositorio.unb.br/handle/10482/42130-
dc.language.isoInglêspt_BR
dc.publisherIEEEpt_BR
dc.rightsAcesso Abertopt_BR
dc.titleFrom feature engineering and topics models to enhanced prediction rates in phishing detectionpt_BR
dc.typeArtigopt_BR
dc.subject.keywordCrime por computadorpt_BR
dc.subject.keywordExtração de recursospt_BR
dc.subject.keywordAprendizado do computadorpt_BR
dc.subject.keywordInteligência artificialpt_BR
dc.subject.keywordProcessamento de linguagem natural (Computação)pt_BR
dc.subject.keywordCorreio eletrônicopt_BR
dc.rights.licenseThis work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/pt_BR
dc.identifier.doi10.1109/ACCESS.2020.2989126pt_BR
dc.description.abstract1Phishing is a type of fraud attempt in which the attacker, usually by e-mail, pretends to be a trusted person or entity in order to obtain sensitive information from a target. Most recent phishing detection researches have focused on obtaining highly distinctive features from the metadata and text of these e-mails. The obtained attributes are then used to feed classification algorithms in order to determine whether they are phishing or legitimate messages. In this paper, it is proposed an approach based on machine learning to detect phishing e-mail attacks. The methods that compose this approach are performed through a feature engineering process based on natural language processing, lemmatization, topics modeling, improved learning techniques for resampling and cross-validation, and hyperparameters configuration. The first proposed method uses all the features obtained from the Document-Term Matrix (DTM) in the classification algorithms. The second one uses Latent Dirichlet Allocation (LDA) as a operation to deal with the problems of the “curse of dimensionality”, the sparsity, and the text context portion included in the obtained representation. The proposed approach reached marks with an F1-measure of 99.95% success rate using the XGBoost algorithm. It outperforms state-of-the-art phishing detection researches for an accredited data set, in applications based only on the body of the e-mails, without using other e-mail features such as its header, IP information or number of links in the text.pt_BR
dc.identifier.orcidhttps://orcid.org/ 0000-0002-2917-3605pt_BR
dc.identifier.orcidhttps://orcid.org/ 0000-0003-1101-3029pt_BR
dc.identifier.orcidhttps://orcid.org/ 0000-0003-0512-374Xpt_BR
dc.identifier.orcidhttps://orcid.org/ 0000-0002-8616-4924pt_BR
dc.identifier.orcidhttps://orcid.org/ 0000-0003-3558-466Xpt_BR
Aparece nas coleções:Artigos publicados em periódicos e afins

Mostrar registro simples do item Visualizar estatísticas



Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.