University of Hertfordshire

By the same authors

Analyzing new features of infected web content in detection of malicious web pages

Research output: Contribution to journalArticlepeer-review

Standard

Analyzing new features of infected web content in detection of malicious web pages. / Hajian, Nezhad; Jahan, Majid Vafaei ; Tayaraninajaran, Mohammadhassan; Sadrnezhad, Z.

In: The ISC International Journal of Information Security, Vol. 9, No. 2, 7, 01.05.2017.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{57ac9790b74f4d13ab168cdb37d08a12,
title = "Analyzing new features of infected web content in detection of malicious web pages",
abstract = "Recent improvements in web standards and technologies enable the attackers to hide and obfuscate infectious codes with new methods and thus escaping the security filters. In this paper, we study the application of machine learning techniques in detecting malicious web pages. In order to detect malicious web pages, we propose and analyze a novel set of features including HTML, JavaScript (jQuery library) and XSS attacks. The proposed features are evaluated on a data set that is gathered by a crawler from malicious web domains, IP and address black lists. For the purpose of evaluation, we use a number of machine learning algorithms. Experimental results show that using the proposed set of features, the C4.5-Tree algorithm offers the best performance with 97.61% accuracy, and F1-measure has 96.75% accuracy. We also rank the quality of the features. Experimental results suggest that nine of the proposed features are among the twenty best discriminative features.",
author = "Nezhad Hajian and Jahan, {Majid Vafaei} and Mohammadhassan Tayaraninajaran and Z. Sadrnezhad",
note = "{\textcopyright} 2017 ISC. All rights reserved. ",
year = "2017",
month = may,
day = "1",
doi = "10.22042/ISECURE.2017.9.2.2",
language = "English",
volume = "9",
journal = "The ISC International Journal of Information Security",
issn = "2008-3076",
publisher = "Iranian Society of Cryptology",
number = "2",

}

RIS

TY - JOUR

T1 - Analyzing new features of infected web content in detection of malicious web pages

AU - Hajian, Nezhad

AU - Jahan, Majid Vafaei

AU - Tayaraninajaran, Mohammadhassan

AU - Sadrnezhad, Z.

N1 - © 2017 ISC. All rights reserved.

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Recent improvements in web standards and technologies enable the attackers to hide and obfuscate infectious codes with new methods and thus escaping the security filters. In this paper, we study the application of machine learning techniques in detecting malicious web pages. In order to detect malicious web pages, we propose and analyze a novel set of features including HTML, JavaScript (jQuery library) and XSS attacks. The proposed features are evaluated on a data set that is gathered by a crawler from malicious web domains, IP and address black lists. For the purpose of evaluation, we use a number of machine learning algorithms. Experimental results show that using the proposed set of features, the C4.5-Tree algorithm offers the best performance with 97.61% accuracy, and F1-measure has 96.75% accuracy. We also rank the quality of the features. Experimental results suggest that nine of the proposed features are among the twenty best discriminative features.

AB - Recent improvements in web standards and technologies enable the attackers to hide and obfuscate infectious codes with new methods and thus escaping the security filters. In this paper, we study the application of machine learning techniques in detecting malicious web pages. In order to detect malicious web pages, we propose and analyze a novel set of features including HTML, JavaScript (jQuery library) and XSS attacks. The proposed features are evaluated on a data set that is gathered by a crawler from malicious web domains, IP and address black lists. For the purpose of evaluation, we use a number of machine learning algorithms. Experimental results show that using the proposed set of features, the C4.5-Tree algorithm offers the best performance with 97.61% accuracy, and F1-measure has 96.75% accuracy. We also rank the quality of the features. Experimental results suggest that nine of the proposed features are among the twenty best discriminative features.

U2 - 10.22042/ISECURE.2017.9.2.2

DO - 10.22042/ISECURE.2017.9.2.2

M3 - Article

VL - 9

JO - The ISC International Journal of Information Security

JF - The ISC International Journal of Information Security

SN - 2008-3076

IS - 2

M1 - 7

ER -