Analysis of Android malware permission based dataset using machine learning

• Author(s) / Creator(s)

  • Ramani, Sushmitha Suruliyandi
  • Naralasetty, Manikanta
  • Avneesh
  • Kothakapu, Ambica
  • Rudraraju, Shainija
  • Nasina, Sai Harish
  • Metla, Sirisha

• Security threats in Android applications have grown in sync with Android’s growth. Machine leaning can be used to add functionality to traditional antivirus systems. Such an approach necessitates the identification and labelling of a large amount of harmful and benign code in advance to use it for model training. The modeling techniques and its practical implementation using the Android Malware Permission based dataset to find whether it is benign, or malware have been proposed in this paper. Random Forest Classifier, Logistic Regression, Decision Tree Classifier, XGB Classifier are the machine learning algorithms implemented in this research. The overall performance of approximately 85% of accuracy has been achieved on the dataset. The dataset is freely available to the research community.

• Date created

  2021-06-23

• Subjects / Keywords

  • machine learning
  • Android malware
  • permission
  • dataset
  • malware

• Type of Item

  Research Material

• DOI

  https://doi.org/10.7939/r3-0d09-xx94

• License

  Attribution-NonCommercial 4.0 International