KLASIFIKASI SMS MALWARE PADA PLATFORM ANDROID MENGGUNAKAN METODE RANDOM FOREST

SITOHANG, JONATHAN JEREMIA VALENTINO VICI and Stiawan, Deris (2022) KLASIFIKASI SMS MALWARE PADA PLATFORM ANDROID MENGGUNAKAN METODE RANDOM FOREST. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181823007.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_56201_09011181823007_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
Preview	Text RAMA_56201_09011181823007_0003047905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB) | Preview
	Text RAMA_56201_09011181823007_0003047905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (986kB) | Request a copy
	Text RAMA_56201_09011181823007_0003047905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011181823007_0003047905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011181823007_0003047905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (610kB) | Request a copy
	Text RAMA_56201_09011181823007_0003047905_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (542kB) | Request a copy
	Text RAMA_56201_09011181823007_0003047905_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Android is one of the most popular mobile platforms in the world as a mobile operating system, still facing security challenges and threats. Android is malware with various variants that are included in application packages that have APK (Android Package Kit) extensions with permission for SMS. SMS (Short Messages Service) is a standard service feature on today's smartphones. The growing technology of Android has this feature, which means that it also opens the gate for available malware variants that can attack SMS services. SMS-based Malware was then discovered in 2012. In short, SMS Malware can perform attacks via SMS and can perform subscriptions to an application silently. This research uses a dataset provided by the Canadian Institute of Cybersecurity which has the BeanBot SMS Malware dataset. The results of the classification use MinMaxScaler normalization and Chi-Square feature selection aimed at getting the best features on the dataset, which are then classified using the Random Forest algorithm. This research uses various variations of split data with test sizes 0.2, 0.3, and 0.4. The classification results of this study show that the Chi-Square feature selection with 30 selected features with a test size of 0.2 gets the best results, namely accuracy of 89.53%, Recall of 93.49%, Precision of 87.39%, False Positive Rate value and the best error value is at test size 0.4 with a False Positive Rate value of 9.67% and Error of 10.46%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Short Message Service, SMS Malware Classification, Random Forest, Machine Learning
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	JONATHAN JEREMIA VALENTINO VICI SITOHANG
Date Deposited:	18 Aug 2022 04:47
Last Modified:	18 Aug 2022 04:48
URI:	http://repository.unsri.ac.id/id/eprint/77402

Actions (login required)

View Item