Android Malware Dataset with VirusTotal Labels

<p>This dataset contains labels of 2.47 million Android apk hashes extracted from VirusTotal reports.</p> <p>The dataset was used in the experiments of our publication titled <a href="https://www.mdpi.com/1424-8220/21/16/5671" rel="nofollow">An Analysis of Android Malware Classification Services<br></a><br>The csv of the labels that was extracted from the VirusTotal reports is provided in&nbsp;<code>labeling_dataset.csv.gz</code>&nbsp;. A cell's value of&nbsp;<code>-1</code>&nbsp;is used whenever there was no result from the<br>engine for the given apk file hash value. The column names are provided in&nbsp;<code>cols_labeling_dataset.csv</code>.</p> <p>Note</p> <p><code>-1</code>&nbsp;is a&nbsp;<code>string</code>&nbsp;and not an&nbsp;<code>integer</code></p> <h2>If you use information from this repo, please cite our paper</h2> <p>Rashed M, Suarez-Tangil G. An Analysis of Android Malware Classification Services. Sensors. 2021; 21(16):5671.&nbsp;<a href="https://doi.org/10.3390/s21165671" rel="nofollow">https://doi.org/10.3390/s21165671</a></p> <h2>BibTeX</h2> <p><code>@Article</code>{s21165671,<br>AUTHOR = {Rashed, Mohammed and Suarez-Tangil, Guillermo},<br>TITLE = {An Analysis of Android Malware Classification Services},<br>JOURNAL = {Sensors},<br>VOLUME = {21},<br>YEAR = {2021},<br>NUMBER = {16},<br>ARTICLE-NUMBER = {5671},<br>URL = {<a href="https://www.mdpi.com/1424-8220/21/16/5671%7D,%5C" rel="nofollow">https://www.mdpi.com/1424-8220/21/16/5671},\</a><br>ISSN = {1424-8220},<br>DOI = {10.3390/s21165671}<br>}</p> <h2>Required Software</h2> <p><code>gzip</code></p> <ul> <li>Debian-based Linux: you may install it using the following command&nbsp;<code>apt-get install gzip</code></li> <li>MacOS:&nbsp;<code>gzip</code>&nbsp;is pre-installed</li> <li>Windows: you may download&nbsp;<code>gzip</code>&nbsp;from&nbsp;<a href="http://gnuwin32.sourceforge.net/packages/gzip.htm" rel="nofollow">http://gnuwin32.sourceforge.net/packages/gzip.htm</a></li> </ul> <h2>How to use the file?</h2> <p>There are two ways to use the file:</p> <ol> <li>Extract the gzip file and then you will have a csv output file. For that you need to install gzip and then extracting .csv.gz. The user may use the command&nbsp;<code>gunzip labelingDataset.csv.gz</code></li> <li>Extract information from the zipped file directly (following the same logic of&nbsp;<a href="https://androzoo.uni.lu/lists" rel="nofollow">AndroZoo's csv</a>):<br>To extract the first column and save to a file called&nbsp;<code>list_of_selected_sha256</code>, run the following command:<br><code>zcat labelingDataset.csv.gz | cut -d',' -f1 &gt; list_of_selected_sha256</code><br>To obtain rows of apk hashes that were first seen after the 1st of May, 2016, run this command:<br><code>zcat labeling_dataset.csv.gz | grep -v ',snaggamea' | awk -F, '{if ( $2 &gt;= "2016-05" ) {print} }'</code></li> </ol>