Saved in:
| Hovedforfatter: | |
|---|---|
| Format: | Recurso digital |
| Sprog: | |
| Udgivet: |
Zenodo
2022
|
| Online adgang: | https://doi.org/10.5281/zenodo.15567139 |
| Tags: |
Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!
|
Indholdsfortegnelse:
- Because of the popularity of Android devices, many attackers spend lots of time and resources creating malicious applications aimed at breaching the security of Android device. Researchers on the other hand have not relented in seeking better ways of curbing attacks on Android devices. In other to achieve an efficient solution, researchers need large datasets to evaluate their solutions. Generating relevant data for this cause is however not an easy task, for this reason, several researchers rely on existing datasets. In this paper, we evaluated the relevance of the feature sets of found in the CICAndMal2017 and DroidFussion datasets. During our study, we discovered the DroidFussion dataset has a higher variance and proved positive on some other parameters tested and as a result performed better. Results from the Random Forest classifier indicates that the Droid dataset achieved 90.0% precisions while the CICAndMal2017 achieved as low as 63% precision when tested following same conditions.