TY - JOUR
T1 - Multimodel Phishing URL Detection Using LSTM, Bidirectional LSTM, and GRU Models
AU - Roy, Sanjiban Sekhar
AU - Awad, Ali Ismail
AU - Amare, Lamesgen Adugnaw
AU - Erkihun, Mabrie Tesfaye
AU - Anas, Mohd
N1 - Publisher Copyright:
© 2022 by the authors.
PY - 2022/11
Y1 - 2022/11
N2 - In today’s world, phishing attacks are gradually increasing, resulting in individuals losing valuables, assets, personal information, etc., to unauthorized parties. In phishing, attackers craft malicious websites disguised as well-known, legitimate sites and send them to individuals to steal personal information and other related private details. Therefore, an efficient and accurate method is required to determine whether a website is malicious. Numerous methods have been proposed for detecting malicious uniform resource locators (URLs) using deep learning, machine learning, and other approaches. In this study, we have used malicious and benign URLs datasets and have proposed a detection mechanism for detecting malicious URLs using recurrent neural network models such as long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), and the gated recurrent unit (GRU). Experimental results have shown that the proposed mechanism achieved an accuracy of 97.0% for LSTM, 99.0% for Bi-LSTM, and 97.5% for GRU, respectively.
AB - In today’s world, phishing attacks are gradually increasing, resulting in individuals losing valuables, assets, personal information, etc., to unauthorized parties. In phishing, attackers craft malicious websites disguised as well-known, legitimate sites and send them to individuals to steal personal information and other related private details. Therefore, an efficient and accurate method is required to determine whether a website is malicious. Numerous methods have been proposed for detecting malicious uniform resource locators (URLs) using deep learning, machine learning, and other approaches. In this study, we have used malicious and benign URLs datasets and have proposed a detection mechanism for detecting malicious URLs using recurrent neural network models such as long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), and the gated recurrent unit (GRU). Experimental results have shown that the proposed mechanism achieved an accuracy of 97.0% for LSTM, 99.0% for Bi-LSTM, and 97.5% for GRU, respectively.
KW - bidirectional LSTM (Bi-LSTM)
KW - gated recurrent unit (GRU) RNN
KW - long short-term memory (LSTM)
KW - phishing URL detection
UR - http://www.scopus.com/inward/record.url?scp=85149488050&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85149488050&partnerID=8YFLogxK
U2 - 10.3390/fi14110340
DO - 10.3390/fi14110340
M3 - Article
AN - SCOPUS:85149488050
SN - 1999-5903
VL - 14
JO - Future Internet
JF - Future Internet
IS - 11
M1 - 340
ER -