Datasets‎ > ‎


Andro-Simnet: Malware classification system based on the similarity network of malware

1. Introduction

Andro-Simnet is an malware classification system based on the similarity network of malware. We applied a social network analysis method to our system so that it can classify malware into one's family accroding to the similar relation of malware. We used features, which are permission, API call sequence, refered file name, activity name, to get the final similarity of malware. Therefore, Andro-Simnet can classify malware samples with signature-based information and behavior-based information.

2. Publication

PST 2018 (The 16th Annual Conference on Privacy, Security and Trust) 

3. Dataset Release

For academic purposes, we are happy to release our dataset. 
To avoid indiscriminate distribution of mobile malware, please send us a request sent by your official email account.

Before downloading it, please read the following instructions carefully.

 (1) The most of samples are zipped using 7zip.

 (2) Then send e-mail to cenda at to get the decompress password. (Please identify your name, affiliation and purpose.) 

 (3) Please use these samples at your own risk.

Contact : Huy Kang Kim (cenda at

§ If you want to download dataset, please fill out the questionnaire at the following URL, We will send you the download URL by e-mail.
§ Textual description of dataset

Dataset Download Link:

4. Acknowledgement

Andro-AutoPsy is developed by Hacking and Countermeasure Research Lab in the Graduate School of Information Security at the Korea University of Korea.

Please contact “Huy Kang Kim” (cenda at if you have any question.