Jorgha Akram Aryandi, - and UNSPECIFIED (2025) RANCANG BANGUN APLIKASI MOBILE BERBASIS MACHINE LEARNING UNTUK DETEKSI MALWARE PADA KONTEN PESAN WHATSAPP. S1 thesis, Universitas Pendidikan Indonesia.
Abstract
Perkembangan teknologi komunikasi yang pesat telah meningkatkan potensi ancaman siber, termasuk penyebaran malware melalui platform pesan instan seperti WhatsApp. Kurangnya kesadaran pengguna terhadap ancaman ini menyebabkan tingginya risiko terhadap serangan siber. Penelitian ini bertujuan untuk merancang dan mengembangkan aplikasi mobile Android berbasis machine learning untuk mendeteksi malware pada File berformat .apk yang dikirim melalui pesan WhatsApp. Model Random Forest digunakan sebagai algoritma klasifikasi, dengan hasil akurasi sebesar 99,05%, serta nilai precision, recall, dan F1-score masing-masing sebesar 0,99 untuk kategori Benign dan Malware, menunjukkan performa klasifikasi yang sangat tinggi dan tingkat kesalahan yang minimal. Aplikasi Android yang dikembangkan berhasil diintegrasikan dengan model Random Forest dan telah diuji menggunakan 15 skenario uji black box, di mana seluruh pengujian berhasil diselesaikan tanpa ditemukan kesalahan. Hasil penelitian ini menunjukkan bahwa aplikasi dapat berfungsi dengan baik dalam mendeteksi File APK berbahaya yang diterima melalui pesan WhatsApp. Diharapkan, aplikasi ini dapat meningkatkan keamanan pengguna WhatsApp terhadap ancaman malware. ------ The rapid development of communication technology has increased the potential for cyber threats, including the spread of malware through instant messaging platforms such as WhatsApp. The lack of user awareness about these threats has resulted in a higher risk of cyberattacks. This research aims to design and develop an Android mobile application based on machine learning to detect malware in .apk Files received through WhatsApp messages. The Random Forest model is used as a classification algorithm, achieving an accuracy of 99.05%, with precision, recall, and F1-score values of 0.99 for both the Benign and Malware categories, demonstrating high classification performance and minimal error rates. The Android application developed was successfully integrated with the Random Forest model and tested using 15 black box test scenarios, where all tests were completed without any errors. The results of this study show that the application functions effectively in detecting harmful APK Files received through WhatsApp messages. It is expected that this application will enhance the security of WhatsApp users against malware threats.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_TEKOM_2110195_Title.pdf Download (474kB) |
|
Text
S_TEKOM_2110195_Chapter1.pdf Download (153kB) |
|
Text
S_TEKOM_2110195_Chapter2.pdf Restricted to Staf Perpustakaan Download (381kB) |
|
Text
S_TEKOM_2110195_Chapter3.pdf Download (787kB) |
|
Text
S_TEKOM_2110195_Chapter4.pdf Restricted to Staf Perpustakaan Download (816kB) |
|
Text
S_TEKOM_2110195_Chapter5.pdf Download (40kB) |
|
Text
S_TEKOM_2110195_Appendix.pdf Restricted to Staf Perpustakaan Download (956kB) |
| Item Type: | Thesis (S1) |
|---|---|
| Additional Information: | https://scholar.google.com/citations?hl=en&user=vZuh-tcAAAAJ ID SINTA Dosen Pembimbing : Munawir : 6745899 Deden Pradeka : 6680849 |
| Uncontrolled Keywords: | Aplikasi Mobile Android, Malware, WhatsApp, Machine Learning, Random Forest, Android Mobile Application |
| Subjects: | L Education > L Education (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | UPI Kampus cibiru > S1 Teknik Komputer |
| Depositing User: | Jorgha Akram Aryandi |
| Date Deposited: | 09 May 2025 03:53 |
| Last Modified: | 09 May 2025 03:53 |
| URI: | http://repository.upi.edu/id/eprint/132909 |
Actions (login required)
 |
View Item |