In this paper, we propose a machine learning approach to
the identification of Android app anomalies. Particularly, we
employ feed-forward neural networks (NNs) [10] to categorize
apps based on their permissions. Our results reveal that NNs
can predict app categories efficiently and reliably. To the best
of our knowledge, this is the first exhaustive work regarding
category verification of Android apps.
The rest of this paper is organized as follows: Section II
presents major novel research on Android app security, section
III explains our experimental dataset and the proposed
methodology to validate app categories, section IV shows our
experiments results, and section V concludes the paper.