The week's pick
Reseach Article
Enhancing Cybersecurity through LSTM-Based Phishing URL Detection
| International Journal of Applied Information Systems |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 12 - Number 46 |
| Year of Publication: 2024 |
| Authors: T.J. Ayo, O.D. Alowolodu, D.P. Omotayo |
10.5120/ijais2024451992
|
T.J. Ayo, O.D. Alowolodu, D.P. Omotayo . Enhancing Cybersecurity through LSTM-Based Phishing URL Detection. International Journal of Applied Information Systems. 12, 46 ( Dec 2024), 1-6. DOI=10.5120/ijais2024451992
Abstract
Attackers over the years has frequently launch attacks on users of the internet in other to steal their personal vital information so as to achieve their fraudulent acts. To curb this attacks there is a need to develop a deep learning model that can conveniently detect URL that are phishing. Long short time memory (LSTM) model is used in this research, various approaches haven used but best result is yet to be preferred the approaches. LSTM is a variation of Recurrent Neural Network (RNN) Architecture designed to handle sequence related prediction problems and its does well when working on sequential data, such as speech recognition, natural language processing and Phishing detection. The two datasets from kaggle.com were used and the result shows that on Phishing_1 dataset (large dataset) has an accuracy of 0.8672 while on the second dataset Phishing_Legitimate_full (small dataset) has an accuracy of 0.9043 this therefore mean that LSTM can perform better on small datasets and there is tendency of result degradation on larger datasets. However, there are other metrics that makes LSTM a considerable model on larger datasets like the F1-score.
References
- Alkhalil, Z., Nawaf, L., & Khan, I. 2021. Phishing attacks: A recent comprehensive study and a new anatomy. Frontiers in Computer Science, 3, Article 563060. https://doi.org/10.3389/fcomp.2021.563060.
- Zanab, S., Jamil, K., and Khan, H. 2021. Identity theft and phishing attacks in the digital age: An empirical study. Journal of Cybersecurity Studies, 9(2), 48-60.
- Burita. (2021). The growing threat of phishing in a connected world. Journal of Information Security and Cyber Crime, 22(3), 85-100.
- Singer, P., and Friedman, A. 2014. Cybersecurity and cyberwar: What everyone needs to know. Oxford University Press.
- Reddy, Kalyani S., and D. Sasikala 2017. "Blacklist-Based Techniques for Detection of Phishing Attacks: A Survey." International Journal of Engineering and Technology.
- Prasanta, B. 2021. An emerging solution for detection of phishing attacks. International Journal of Computer Applications,181(6),11-16.doi.org/10.5120/ijca 2021921313.
- Kamal, H., Stewart, A., and Rehn, M. 2022. The applications of deep learning in material sciences: A comprehensive review. Journal of Materials Science and Technology, 30(2), 89-115.
- Asmaa, R., Ahmed, H., and Saleh, M. 2023. From phishing behavior analysis and feature selection to enhance prediction rate in phishing detection. Journal of Information Security and Applications, 72, 103031. https://doi.org/10.1016/j.jisa.2023.103031.
- Kulkarni, A. 2022. Convolution neural networks for phishing detection. International Journal of Advanced Computer Science and Applications, 14(4). https://doi.org/10.14569/IJACSA.2023.0140403
Index Terms
Keywords