Elsa Maulina Sari, . (2025) WEBSITE PENDETEKSI PHISHING WHATSAPP BERDASARKAN ANALISIS 5 ALGORITMA MACHINE LEARNING. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (250kB) |
|
Text
AWAL.pdf Download (617kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (266kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (838kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (702kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
BAB 5.pdf Download (341kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (227kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (142kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository UPNVJ Only Download (36MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository UPNVJ Only Download (392kB) |
|
Text
AWAL.pdf Download (617kB) |
Abstract
Phishing is an evolving cybersecurity threat that employs increasingly complex deception techniques. WhatsApp, as a widely used communication platform, has become a prime target for such attacks. This study aims to detect anomalies in phishing URLs using five machine learning algorithms: Isolation Forest, Neural Network, Random Forest, Support Vector Machine (SVM), and XGBoost. The dataset, obtained from Kaggle, consists of 11,430 classified URLs and is divided using an 80:10:10 ratio for training, validation, and testing. The evaluation is based on four key performance metrics: accuracy, precision, recall, and Area Under Curve (AUC). The results show that the Neural Network algorithm outperforms the others, achieving 97% accuracy on the training set, 92% on validation, and 93% on testing. This model is implemented in a web-based application using the Flask framework, with a prediction threshold of 0.5—URLs with probabilities below this threshold are classified as legitimate, and those above are classified as phishing. The application is capable of identifying URLs in real time with high accuracy, effectively supporting phishing prevention on WhatsApp.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | No. Panggil: 2110314093 Pembimbing: Yosy Rahmawati Penguji 1: Fajar Rahayu Ikhwanul Penguji 2: Ni Putu Devira Ayu |
| Uncontrolled Keywords: | Algorithm Machine Learning, Detection Phishing, Flask, Isolation Forest, Neural Network, Random Forest, Support Vector Machine, WhatsApp, XGBoost. |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Teknik > Program Studi Teknik Elektro (S1) |
| Depositing User: | ELSA MAULINA SARI |
| Date Deposited: | 22 Jul 2025 07:47 |
| Last Modified: | 22 Jul 2025 07:47 |
| URI: | http://repository.upnvj.ac.id/id/eprint/38240 |
Actions (login required)
 |
View Item |