xr-droid: A Benchmark Dataset for AR/VR and Security Applications

Citation Author(s):
Abdulaziz
Alghamdi
Ali
Alkinoon
Ahod
Alghuried
David
Mohaisen
Submitted by:
Abdulaziz Alghamdi
Last updated:
Mon, 05/20/2024 - 12:04
DOI:
10.21227/za5x-8h95
License:
0
0 ratings - Please login to submit your rating.

Abstract 

The development of metaverses and virtual worlds on various platforms, including mobile devices, has led to the growth of applications in virtual reality (VR) and augmented reality (AR) in recent years. This application growth is paralleled by a growth of interest in analyzing and understanding AR/VR applications from security and performance standpoints. Despite this growing interest, benchmark datasets are lacking to facilitate this research pursuit. In this paper, we collect a dataset that consists of 408 diverse AR/VR applications from the Google Play Store and acquire various data modalities associated with those applications standardized in the form of seven features: control flow graphs, strings, functions, permissions, API calls, hexdump, and metadata. We highlight various research endeavors (applications) that can benefit from our dataset for each data modality.

Instructions: 

The dataset comprises seven folders and one standalone document. The initial folder, named APK, includes 408 APK samples. The second folder, designated as CFG (Control Flow Graph), contains 408 subfolders, each corresponding to an APK file. The third folder, labeled API (Application Programming Interface) calls, encompasses 408 CSV documents detailing API calls. Following this, the functions folder holds 408 JSON documents, each representing functions within an APK. The fifth folder, hexdump, contains 408 text documents. The sixth folder, strings, is organized into two subfolders for different formats: CSV and Excel, each containing strings data from the APKs in CSV and XLSX formats respectively. The penultimate folder is dedicated to privacy policies, featuring 302 text documents. Lastly, the standalone document compiles all APK permissions in a CSV format. This structure facilitates a comprehensive analysis of the APK files across various dimensions.