MiMaLo: advanced normalization method for mobile malware detection
A range of research procedures have been executed to overcome malware attacks. This research used a malware behavior observe approach on device calls on mobile devices operating gadget kernel. An application used to be mounted on mobile gadget to gather facts and processed them to get dataset. This...
保存先:
| 主要な著者: | , , , , |
|---|---|
| フォーマット: | 論文 |
| 言語: | English |
| 出版事項: |
Modern Education and Computer Science Press
2022
|
| オンライン･アクセス: | http://eprints.utem.edu.my/id/eprint/26498/2/IJMECS-V14-N5-3.PDF http://eprints.utem.edu.my/id/eprint/26498/ https://www.mecs-press.org/ijmecs/ijmecs-v14-n5/IJMECS-V14-N5-3.pdf |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 要約: | A range of research procedures have been executed to overcome malware attacks. This research used a malware behavior observe approach on device calls on mobile devices operating gadget kernel. An application used to be mounted on mobile gadget to gather facts and processed them to get dataset. This research used data mining classification approach method and validates it using ten fold cross validation. MiMaLo is a method to normalize a dataset the usage of the min-max aggregate and logarithm function. The application of the MiMaLo method aims to increase the accuracy value. Derived from the experiments, the classifiers overall performance level used to be extensively increasing. The application of the MiMaLo method using the neural network algorithm produces an accuracy of 93.54% with AUC of 0.982. |
|---|