Download PDFOpen PDF in browser

Android Malware Detection using Deep Learning

EasyChair Preprint no. 7694

13 pagesDate: April 2, 2022


A large part of Android's popularity is due to the ease with which it can be operated and the wide range of capabilities it offers its users, both of which have made it a prime target for cyber thieves. Recent malware may get through the cracks of Android's traditional anti-malware solutions, such as those that rely on signatures or monitor power use. This new method uses NEURAL Networks and the KMEANS algorithm to develop a predictive analytics model to identify virus in Android applications. By extracting the permissions list from the Android APK file, we can use these two techniques to detect malware in Android apps. We use the Android Permission Features dataset to develop and evaluate our strategy. Our deep learning method exceeds other methods with a 99 percent accuracy rate, according to the results of our tests. Static analysis, API-calls, and permissions are all examples of Android malware.

Keyphrases: Android, deep learning, Malware

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Gudla Surya Bharti and Syed Shabeeb Nibras and Mukkamala Shyam Srujan and Kesanapalli V K Raghavendra Chowdary and Siriki Bala Murali},
  title = {Android Malware Detection using Deep Learning},
  howpublished = {EasyChair Preprint no. 7694},

  year = {EasyChair, 2022}}
Download PDFOpen PDF in browser