An intelligent spam detection model based on artificial immune system

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Spam emails, also known as non-self, are unsolicited commercial or malicious emails, sent to affect either a single individual or a corporation or a group of people. Besides advertising, these may contain links to phishing or malware hosting websites set up to steal confidential information. In this paper, a study of the effectiveness of using a Negative Selection Algorithm (NSA) for anomaly detection applied to spam filtering is presented. NSA has a high performance and a low false detection rate. The designed framework intelligently works through three detection phases to finally determine an email's legitimacy based on the knowledge gathered in the training phase. The system operates by elimination through Negative Selection similar to the functionality of T-cells' in biological systems. It has been observed that with the inclusion of more datasets, the performance continues to improve, resulting in a 6% increase of True Positive and True Negative detection rate while achieving an actual detection rate of spam and ham of 98.5%. The model has been further compared against similar studies, and the result shows that the proposed system results in an increase of 2 to 15% in the correct detection rate of spam and ham.

Original languageEnglish
Article number209
Pages (from-to)1-17
Number of pages17
JournalInformation (Switzerland)
Volume10
Issue number6
DOIs
Publication statusPublished - 12 Jun 2019

Fingerprint

Immune system
Electronic mail
T-cells
Biological systems
Websites
Marketing
Industry

Cite this

@article{64ae694bf78943258e835564fb2d951b,
title = "An intelligent spam detection model based on artificial immune system",
abstract = "Spam emails, also known as non-self, are unsolicited commercial or malicious emails, sent to affect either a single individual or a corporation or a group of people. Besides advertising, these may contain links to phishing or malware hosting websites set up to steal confidential information. In this paper, a study of the effectiveness of using a Negative Selection Algorithm (NSA) for anomaly detection applied to spam filtering is presented. NSA has a high performance and a low false detection rate. The designed framework intelligently works through three detection phases to finally determine an email's legitimacy based on the knowledge gathered in the training phase. The system operates by elimination through Negative Selection similar to the functionality of T-cells' in biological systems. It has been observed that with the inclusion of more datasets, the performance continues to improve, resulting in a 6{\%} increase of True Positive and True Negative detection rate while achieving an actual detection rate of spam and ham of 98.5{\%}. The model has been further compared against similar studies, and the result shows that the proposed system results in an increase of 2 to 15{\%} in the correct detection rate of spam and ham.",
keywords = "Anomaly detection, Ham, Negative Selection, Phishing, Spam",
author = "Saleh, {Abdul Jabbar} and Asif Karim and Bharanidharan Shanmugam and Sami Azam and Krishnan Kannoorpatti and Mirjam Jonkman and {De Boer}, Friso",
year = "2019",
month = "6",
day = "12",
doi = "10.3390/info10060209",
language = "English",
volume = "10",
pages = "1--17",
journal = "Information (Basel)",
issn = "2078-2489",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "6",

}

An intelligent spam detection model based on artificial immune system. / Saleh, Abdul Jabbar; Karim, Asif; Shanmugam, Bharanidharan; Azam, Sami; Kannoorpatti, Krishnan; Jonkman, Mirjam; De Boer, Friso.

In: Information (Switzerland), Vol. 10, No. 6, 209, 12.06.2019, p. 1-17.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - An intelligent spam detection model based on artificial immune system

AU - Saleh, Abdul Jabbar

AU - Karim, Asif

AU - Shanmugam, Bharanidharan

AU - Azam, Sami

AU - Kannoorpatti, Krishnan

AU - Jonkman, Mirjam

AU - De Boer, Friso

PY - 2019/6/12

Y1 - 2019/6/12

N2 - Spam emails, also known as non-self, are unsolicited commercial or malicious emails, sent to affect either a single individual or a corporation or a group of people. Besides advertising, these may contain links to phishing or malware hosting websites set up to steal confidential information. In this paper, a study of the effectiveness of using a Negative Selection Algorithm (NSA) for anomaly detection applied to spam filtering is presented. NSA has a high performance and a low false detection rate. The designed framework intelligently works through three detection phases to finally determine an email's legitimacy based on the knowledge gathered in the training phase. The system operates by elimination through Negative Selection similar to the functionality of T-cells' in biological systems. It has been observed that with the inclusion of more datasets, the performance continues to improve, resulting in a 6% increase of True Positive and True Negative detection rate while achieving an actual detection rate of spam and ham of 98.5%. The model has been further compared against similar studies, and the result shows that the proposed system results in an increase of 2 to 15% in the correct detection rate of spam and ham.

AB - Spam emails, also known as non-self, are unsolicited commercial or malicious emails, sent to affect either a single individual or a corporation or a group of people. Besides advertising, these may contain links to phishing or malware hosting websites set up to steal confidential information. In this paper, a study of the effectiveness of using a Negative Selection Algorithm (NSA) for anomaly detection applied to spam filtering is presented. NSA has a high performance and a low false detection rate. The designed framework intelligently works through three detection phases to finally determine an email's legitimacy based on the knowledge gathered in the training phase. The system operates by elimination through Negative Selection similar to the functionality of T-cells' in biological systems. It has been observed that with the inclusion of more datasets, the performance continues to improve, resulting in a 6% increase of True Positive and True Negative detection rate while achieving an actual detection rate of spam and ham of 98.5%. The model has been further compared against similar studies, and the result shows that the proposed system results in an increase of 2 to 15% in the correct detection rate of spam and ham.

KW - Anomaly detection

KW - Ham

KW - Negative Selection

KW - Phishing

KW - Spam

UR - http://www.scopus.com/inward/record.url?scp=85067459956&partnerID=8YFLogxK

U2 - 10.3390/info10060209

DO - 10.3390/info10060209

M3 - Article

VL - 10

SP - 1

EP - 17

JO - Information (Basel)

JF - Information (Basel)

SN - 2078-2489

IS - 6

M1 - 209

ER -