Deteksi Deteksi email phishing berdasarkan pemilihan fitur pencarian biner
Abstract
Phishing attacks have emerged as a significant threat in the cybersecurity landscape, with email being a primary channel exploited by attackers to deceive victims. This study proposes an innovative phishing email detection method utilizing Binary Search Feature Selection (BSFS) combined with the Pearson correlation coefficient as a feature ranking technique. The proposed method leverages four feature dimensions: email subject, body, hyperlinks, and content readability, resulting in the selection of 41 relevant features. Experimental results demonstrate that BSFS achieves the highest accuracy of 97.41%, surpassing Sequential Forward Floating Selection (SFFS) at 95.63% and Wrapper Feature Selection (WFS) at 95.56%. While SFFS requires more computational time to identify the optimal feature set, and WFS offers the fastest computation but with lower accuracy, BSFS provides the best balance between detection accuracy and computational efficiency. The key contribution of this research lies in the development of an efficient feature selection method that can be adapted for large-scale phishing detection systems, offering superior performance despite reducing the number of features utilized.
Downloads
References
Abdelhamid N, Ayesh A, Thabtah F. Phishing detection based associative classification data mining. Expert Syst Appl. 2014;41(13):5948–59 https://www.sciencedirect.com/science/article/abs/pii/S0957417414001481?via%3Dihub
Akinyelu AA, Adewumi AO. Classification of phishing email using random forest machine learning technique. J Appl Math. 2014;2014:425731. https://onlinelibrary.wiley.com/doi/10.1155/2014/42573
lmomani A, Gupta B, Atawneh S, Meulenberg A, Almomani E. A survey of phishing email filtering techniques. IEEE Commun Surv Tutor. 2013;15(4):2070–90. https://ieeexplore.ieee.org/document/6489877
Afroz S, Greenstadt R. Phishzoo: detecting phishing websites by looking at them. In: 2011 fifth IEEE international conference on semantic computing (ICSC); 2011. p. 368–75. https://doi.org/10.1109/ICSC.2011.52
Copyright (c) 2025 Ahmad Harits Albaihaqi
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
