A dynamic self-structuring neural network model to combat phishing

Fadi Thabtah, Rami M. Mohammad, Thomas McCluskey

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Creating a neural network based classification model is commonly accomplished using the trial and error technique. However, this technique has several difficulties in terms of time wasted and the availability of experts. In this article, an algorithm that simplifies structuring neural network classification models is proposed. The algorithm aims at creating a large enough structure to learn models from the training dataset that can be generalised on the testing dataset. Our algorithm dynamically tunes the structure parameters during the training phase aiming to derive accurate non-overfitting classifiers. The proposed algorithm has been applied to phishing website classification problem and it shows competitive results with respect to various evaluation measures such as harmonic mean (F1-score), precision, and classification accuracy.
Original languageEnglish
Title of host publication2016 International Joint Conference on Neural Networks (IJCNN)
PublisherIEEE
Pages72-77
Number of pages6
ISBN (Electronic)9781509006205, 9781509006199
ISBN (Print)9781509006212
DOIs
Publication statusPublished - 3 Nov 2016
Event2016 International Joint Conference on Neural Networks - Vancouver, Canada
Duration: 24 Jul 201629 Jul 2016

Publication series

NameIJCNN
PublisherIEEE
ISSN (Electronic)2161-4407

Conference

Conference2016 International Joint Conference on Neural Networks
Abbreviated titleIJCNN
CountryCanada
Period24/07/1629/07/16

Fingerprint

Neural networks
Websites
Classifiers
Availability
Testing

Cite this

Thabtah, F., Mohammad, R. M., & McCluskey, T. (2016). A dynamic self-structuring neural network model to combat phishing. In 2016 International Joint Conference on Neural Networks (IJCNN) (pp. 72-77). (IJCNN). IEEE. https://doi.org/10.1109/IJCNN.2016.7727750
Thabtah, Fadi ; Mohammad, Rami M. ; McCluskey, Thomas. / A dynamic self-structuring neural network model to combat phishing. 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 2016. pp. 72-77 (IJCNN).
@inproceedings{c80c0900f2dc4d3789e5b537af40d5f2,
title = "A dynamic self-structuring neural network model to combat phishing",
abstract = "Creating a neural network based classification model is commonly accomplished using the trial and error technique. However, this technique has several difficulties in terms of time wasted and the availability of experts. In this article, an algorithm that simplifies structuring neural network classification models is proposed. The algorithm aims at creating a large enough structure to learn models from the training dataset that can be generalised on the testing dataset. Our algorithm dynamically tunes the structure parameters during the training phase aiming to derive accurate non-overfitting classifiers. The proposed algorithm has been applied to phishing website classification problem and it shows competitive results with respect to various evaluation measures such as harmonic mean (F1-score), precision, and classification accuracy.",
keywords = "Neurons, Artificial neural network, density estimation robust algorithm, Classification algorithms, biological neural networks, heuristic algorithms",
author = "Fadi Thabtah and Mohammad, {Rami M.} and Thomas McCluskey",
note = "Has ISBN and ISSN. Accepted March 2016. HN 24/10/2016",
year = "2016",
month = "11",
day = "3",
doi = "10.1109/IJCNN.2016.7727750",
language = "English",
isbn = "9781509006212",
series = "IJCNN",
publisher = "IEEE",
pages = "72--77",
booktitle = "2016 International Joint Conference on Neural Networks (IJCNN)",

}

Thabtah, F, Mohammad, RM & McCluskey, T 2016, A dynamic self-structuring neural network model to combat phishing. in 2016 International Joint Conference on Neural Networks (IJCNN). IJCNN, IEEE, pp. 72-77, 2016 International Joint Conference on Neural Networks, Canada, 24/07/16. https://doi.org/10.1109/IJCNN.2016.7727750

A dynamic self-structuring neural network model to combat phishing. / Thabtah, Fadi; Mohammad, Rami M.; McCluskey, Thomas.

2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 2016. p. 72-77 (IJCNN).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A dynamic self-structuring neural network model to combat phishing

AU - Thabtah, Fadi

AU - Mohammad, Rami M.

AU - McCluskey, Thomas

N1 - Has ISBN and ISSN. Accepted March 2016. HN 24/10/2016

PY - 2016/11/3

Y1 - 2016/11/3

N2 - Creating a neural network based classification model is commonly accomplished using the trial and error technique. However, this technique has several difficulties in terms of time wasted and the availability of experts. In this article, an algorithm that simplifies structuring neural network classification models is proposed. The algorithm aims at creating a large enough structure to learn models from the training dataset that can be generalised on the testing dataset. Our algorithm dynamically tunes the structure parameters during the training phase aiming to derive accurate non-overfitting classifiers. The proposed algorithm has been applied to phishing website classification problem and it shows competitive results with respect to various evaluation measures such as harmonic mean (F1-score), precision, and classification accuracy.

AB - Creating a neural network based classification model is commonly accomplished using the trial and error technique. However, this technique has several difficulties in terms of time wasted and the availability of experts. In this article, an algorithm that simplifies structuring neural network classification models is proposed. The algorithm aims at creating a large enough structure to learn models from the training dataset that can be generalised on the testing dataset. Our algorithm dynamically tunes the structure parameters during the training phase aiming to derive accurate non-overfitting classifiers. The proposed algorithm has been applied to phishing website classification problem and it shows competitive results with respect to various evaluation measures such as harmonic mean (F1-score), precision, and classification accuracy.

KW - Neurons

KW - Artificial neural network

KW - density estimation robust algorithm

KW - Classification algorithms

KW - biological neural networks

KW - heuristic algorithms

U2 - 10.1109/IJCNN.2016.7727750

DO - 10.1109/IJCNN.2016.7727750

M3 - Conference contribution

SN - 9781509006212

T3 - IJCNN

SP - 72

EP - 77

BT - 2016 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

ER -

Thabtah F, Mohammad RM, McCluskey T. A dynamic self-structuring neural network model to combat phishing. In 2016 International Joint Conference on Neural Networks (IJCNN). IEEE. 2016. p. 72-77. (IJCNN). https://doi.org/10.1109/IJCNN.2016.7727750