RANCANG BANGUN APLIKASI ANDROID PENDETEKSI PHISHING DENGAN 3 ALGORITMA MACHINE LEARNING

Faiz Daffa Makarim, . (2026) RANCANG BANGUN APLIKASI ANDROID PENDETEKSI PHISHING DENGAN 3 ALGORITMA MACHINE LEARNING. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

	Text ABSTRAK.pdf Download (229kB)
	Text AWAL.pdf Download (869kB)
	Text BAB 1.pdf Restricted to Repository UPNVJ Only Download (253kB)
	Text BAB 2.pdf Restricted to Repository UPNVJ Only Download (528kB)
	Text BAB 3.pdf Restricted to Repository UPNVJ Only Download (310kB)
	Text BAB 4.pdf Restricted to Repository UPNVJ Only Download (913kB)
	Text BAB 5.pdf Download (226kB)
	Text DAFTAR PUSTAKA.pdf Download (134kB)
	Text RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (97kB)
	Text LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (766kB)
	Text HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (11MB)
	Text ARTIKEL KI.pdf Restricted to Repository staff only Download (226kB)

Abstract

Phishing is one of the continuously evolving cybersecurity threats. At the same time, the use of Android devices as a platform for digital services increases the risk of phishing attacks. This study compares the performance of Long Short-Term Memory (LSTM), Random Forest, and Extreme Gradient Boosting (XGBoost) algorithms in detecting phishing URLs and to analyze the service performance of an Android application implementing these machine learning models. Model evaluation was conducted using accuracy, precision, recall, and Area Under the Curve (AUC) metrics. The application's service performance was evaluated using response time, error rate, and throughput parameters. The results show that XGBoost achieved the best performance with an accuracy of 95.05%, precision of 96.78%, recall of 93.20%, and an AUC score of 0.9902. From the Android system service perspective, the application successfully handled all testing scenarios with a 0% error rate and consistently delivered stable phishing detection results. The findings indicate that the integration of machine learning into Android applications can be effectively utilized for phishing detection, providing high classification accuracy and good service performance.

Item Type:	Thesis (Skripsi)
Additional Information:	[No. panggil 2210314097] [ Pembimbing 1: Silvia Anggraeni} {Pembimbing 2: Andhika Octa Indarso} {Penguji 1:Muhamad Alif Razi} {Penguji 2 :Subekti Ari Santoso}
Uncontrolled Keywords:	Android, Machine Learning, Phishing Detection, LSTM, Random Forest, XGBoost
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User:	FAIZ DAFFA MAKARIM
Date Deposited:	28 Aug 2026 03:13
Last Modified:	28 Aug 2026 03:13
URI:	http://repository.upnvj.ac.id/id/eprint/52531

Actions (login required)

View Item