Phishing URLs Detection using advanced Deep Learning models
Volume 18, Issue 1, 2024
Download| Author(s): |
M. Imran Saeed Department of Software Engineering, Mohammad Ali Jinnah University, imran.saeed@jinnah.edu Muhammad Shakir Department of Robotics and AI, SZABIST Karachi, muhammad.shakir@szabist.edu.pk Syed Hassan Ali Department of Robotics and AI, SZABIST Karachi, hassan.ali@szabist.edu.pk M. Tahir Shaikh Department of Software Engineering, Mohammad Ali Jinnah University, m.Tahir@jinnah.edu |
|---|---|
| Abstract | Phishing, a misleading tactic employed by hackers, involves the manipulation of users through emails, URLs, or messages to extract their personal information. When a deceptive website takes off the layout of a recognized site but operates from a different location, it is referred to as a phishing website. Through extensive research encompassing resources such as Springer, Elsevier, IEEE, and other scholarly journals, numerous techniques have been identified for detecting and preventing phishing attacks. These techniques involve scrutinizing login forms, URLs, and HTML code, differentiating them from the valid dataset used to train reliable models. To counter the ever-evolving strategies devised by phishers to overcome anti-phishing defenses, novel research endeavors are being proposed. The purpose of this research is to produce a novel method for recognizing phishing websites across multiple datasets. Various tactics are under consideration to effectively counter the spread of phishing websites. DL techniques are now being utilized to identify and counteract the dangers presented by malicious websites. Each model's effectiveness is evaluated and compared based on precise assessment results. To detect phishing attacks the models, include support vector machines (SVM), XG Boost, multilayer perceptron’s, decision trees and random forests. This study determines the models that exhibit the highest accuracy in identifying phishing attacks. Building upon the evaluation of several protective measures, a new technique is proposed in this research. This proposed technique holds the potential to advance the creation of more resilient self-learning anti-phishing security systems, ultimately bolstering their efficacy. |
| Keywords | deep learning models, phishing, URL, websites |
| Year | 2024 |
| Volume | 18 |
| Issue | 1 |
| Type | Research paper, manuscript, article |
| Journal Name | Journal of Information & Communication Technology | Publisher Name | ILMA University | Jel Classification | - | DOI | - | ISSN no (E, Electronic) | 2075-7239 | ISSN no (P, Print) | 2415-0169 | Country | Pakistan | City | Karachi | Institution Type | University | Journal Type | Open Access | Manuscript Processing | Blind Peer Reviewed | Format | Paper Link | https://jict.ilmauniversity.edu.pk/journal/jict/18.1/4.pdf | Page |