Intelligent web-phishing detection and protection scheme using integrated features of Images, frames and text

M. A. Adebowale, K. T. Lwin, E. Sánchez, M. A. Hossain

Research output: Contribution to journalReview article

110 Downloads (Pure)

Abstract

A phishing attack is one of the most significant problems faced by online users because of its enormous effect on the online activities performed. In recent years, phishing attacks continue to escalate in frequency, severity and impact. Several solutions, using various methodologies, have been proposed in the literature to counter the web-phishing threats. Notwithstanding, the existing technology cannot detect the new phishing attacks accurately due to the insufficient integration of features of the text, image and frame in the evaluation process. The use of related features of images, frames and text of legitimate and non-legitimate websites and associated artificial intelligence algorithms to develop an integrated method to address these together. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) based robust scheme using the integrated features of the text, images and frames for web-phishing detection and protection. The proposed solution achieves 98.3% accuracies. To our best knowledge, this is the first work that considers the best-integrated text, image and frame feature based solution for phishing detection scheme.

Original languageEnglish
Pages (from-to)300-313
Number of pages14
JournalExpert Systems with Applications
Volume115
Early online date4 Aug 2018
DOIs
Publication statusPublished - 31 Jan 2019

Fingerprint

Fuzzy inference
Artificial intelligence
Websites

Cite this

@article{820d32a1b2cb4a37a421d7de139fbb5e,
title = "Intelligent web-phishing detection and protection scheme using integrated features of Images, frames and text",
abstract = "A phishing attack is one of the most significant problems faced by online users because of its enormous effect on the online activities performed. In recent years, phishing attacks continue to escalate in frequency, severity and impact. Several solutions, using various methodologies, have been proposed in the literature to counter the web-phishing threats. Notwithstanding, the existing technology cannot detect the new phishing attacks accurately due to the insufficient integration of features of the text, image and frame in the evaluation process. The use of related features of images, frames and text of legitimate and non-legitimate websites and associated artificial intelligence algorithms to develop an integrated method to address these together. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) based robust scheme using the integrated features of the text, images and frames for web-phishing detection and protection. The proposed solution achieves 98.3{\%} accuracies. To our best knowledge, this is the first work that considers the best-integrated text, image and frame feature based solution for phishing detection scheme.",
author = "Adebowale, {M. A.} and Lwin, {K. T.} and E. S{\'a}nchez and Hossain, {M. A.}",
year = "2019",
month = "1",
day = "31",
doi = "10.1016/j.eswa.2018.07.067",
language = "English",
volume = "115",
pages = "300--313",
journal = "Expert Systems With Applications.",
issn = "0957-4174",
publisher = "Elsevier",

}

Intelligent web-phishing detection and protection scheme using integrated features of Images, frames and text. / Adebowale, M. A.; Lwin, K. T.; Sánchez, E.; Hossain, M. A.

In: Expert Systems with Applications, Vol. 115, 31.01.2019, p. 300-313.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Intelligent web-phishing detection and protection scheme using integrated features of Images, frames and text

AU - Adebowale, M. A.

AU - Lwin, K. T.

AU - Sánchez, E.

AU - Hossain, M. A.

PY - 2019/1/31

Y1 - 2019/1/31

N2 - A phishing attack is one of the most significant problems faced by online users because of its enormous effect on the online activities performed. In recent years, phishing attacks continue to escalate in frequency, severity and impact. Several solutions, using various methodologies, have been proposed in the literature to counter the web-phishing threats. Notwithstanding, the existing technology cannot detect the new phishing attacks accurately due to the insufficient integration of features of the text, image and frame in the evaluation process. The use of related features of images, frames and text of legitimate and non-legitimate websites and associated artificial intelligence algorithms to develop an integrated method to address these together. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) based robust scheme using the integrated features of the text, images and frames for web-phishing detection and protection. The proposed solution achieves 98.3% accuracies. To our best knowledge, this is the first work that considers the best-integrated text, image and frame feature based solution for phishing detection scheme.

AB - A phishing attack is one of the most significant problems faced by online users because of its enormous effect on the online activities performed. In recent years, phishing attacks continue to escalate in frequency, severity and impact. Several solutions, using various methodologies, have been proposed in the literature to counter the web-phishing threats. Notwithstanding, the existing technology cannot detect the new phishing attacks accurately due to the insufficient integration of features of the text, image and frame in the evaluation process. The use of related features of images, frames and text of legitimate and non-legitimate websites and associated artificial intelligence algorithms to develop an integrated method to address these together. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) based robust scheme using the integrated features of the text, images and frames for web-phishing detection and protection. The proposed solution achieves 98.3% accuracies. To our best knowledge, this is the first work that considers the best-integrated text, image and frame feature based solution for phishing detection scheme.

UR - http://www.scopus.com/inward/record.url?scp=85051681821&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2018.07.067

DO - 10.1016/j.eswa.2018.07.067

M3 - Review article

AN - SCOPUS:85051681821

VL - 115

SP - 300

EP - 313

JO - Expert Systems With Applications.

JF - Expert Systems With Applications.

SN - 0957-4174

ER -