SUPR
Android Malware Detection Using Transformer
Dnr:

NAISS 2024/22-907

Type:

NAISS Small Compute

Principal Investigator:

Hantang Zhang

Affiliation:

Umeå universitet

Start Date:

2024-06-25

End Date:

2025-07-01

Primary Classification:

10201: Computer Sciences

Webpage:

Allocation

Abstract

we propose two empirical studies to (1) detect Android malware and (2) classify Android malware into families. We first (1) reproduce the results of MalBERT using BERT models learning with Android application’s manifests obtained from 265k applications (vs. 22k for MalBERT) from the AndroZoo dataset in order to detect malware. Then we plan to investigate if Transformer can be used to classify Android malware into families. We also want to demonstrate that Android permissions are not what allows Transformer to successfully classify and even that it does not actually need it.