Feed Forward MLP SPAM domain Detection Using Authoritative DNS Records and Email Log

Sharma, Chirag (2020) Feed Forward MLP SPAM domain Detection Using Authoritative DNS Records and Email Log. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (973kB) | Preview
Preview	PDF (Configuration manual) Download (992kB) | Preview

Abstract

Email has been the main source of business communication. Online data loss prevention vendors estimate about 15% of global email space contributes to spam. With emergence of new and highly adaptive spams, attackers leverage the botnets creating large IP address pool which can be used for domain spoofing and prevent domain takedown. There has been development of new technologies such as SPF and DKIM to provide sender authenticity and integrity, but they are not sufficient themselves for spam filtering and the policies related to SPF and DKIM cannot be harsh because these technologies have not been implemented fully by each of reputable domains hence it could lead to most of the legitimate emails undelivered. To solve this problem, this paper proposes the mechanism of detection of spam domains using machine learning with use of Email characteristics such as DKIM signature domain, List-Unsubscribe feature and active DNS records such as SPF record, Authoritative nameservers etc. We have been able to achieve 97.11% accuracy by applying Feed Forward Neural Network machine learning model and with accuracy of 95% which is more than the previous study by taking into consideration List-unsubscribe feature which is actively used by spam domains.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Caoimhe Ní Mhaicín
Date Deposited:	31 Mar 2020 11:52
Last Modified:	31 Mar 2020 11:52
URI:	https://norma.ncirl.ie/id/eprint/4152

Actions (login required)

View Item