Klasifikasi Malware Family menggunakan Metode k-Nearest Neighbor (k-NN)

Smartphones based on Android OS have the most users today because they are
comfortable to use and offer a variety of features. As a result, many malware developers have
made Android OS their main target. Every year, new types of malware families emerge that have
not been recognized. Many researchers are proposing an Android malware analysis framework
using data mining techniques to identify new types of malware families. The researchers needed
an inclusive Android dataset to assess their Android analyzer. In 2019, the Canadian Institute for
Cyber security (CIC) has created a public dataset called CICAndMal2019. This dataset is created
by performing static and dynamic analysis on an actual smartphone. The results of the analysis
then carried out the malware classification using the random forest method. In the classification
of malware family, this study resulted in a precision of 61.2% and a recall of 57.7%. In this paper,
we classify the malware family using the CICAndMal2019 dataset using the k-Nearest Neighbor
(k-NN) method, the results we get a precision of 83% and a recall of 65%.