Skip navigation
Please use this identifier to cite or link to this item: http://repositorio.unb.br/handle/10482/42130
Files in This Item:
File Description SizeFormat 
ARTIGO_FeatureEngineeringTopics.pdf6,96 MBAdobe PDFView/Open
Title: From feature engineering and topics models to enhanced prediction rates in phishing detection
Authors: Gualberto, Éder Souza
Souza Júnior, Rafael Timóteo de
Vieira, Thiago Pereira de Brito
Costa, João Paulo Carvalho Lustosa da
Duque, Cláudio Gottschalg
metadata.dc.identifier.orcid: https://orcid.org/ 0000-0002-2917-3605
https://orcid.org/ 0000-0003-1101-3029
https://orcid.org/ 0000-0003-0512-374X
https://orcid.org/ 0000-0002-8616-4924
https://orcid.org/ 0000-0003-3558-466X
Assunto:: Crime por computador
Extração de recursos
Aprendizado do computador
Inteligência artificial
Processamento de linguagem natural (Computação)
Correio eletrônico
Issue Date: 21-Apr-2021
Publisher: IEEE
Citation: GUALBERTO, 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.
Abstract: Phishing 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.
Licença:: This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
DOI: 10.1109/ACCESS.2020.2989126
Appears in Collections:Artigos publicados em periódicos e afins

Show full item record " class="statisticsLink btn btn-primary" href="/jspui/handle/10482/42130/statistics">



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.