Download Android Application Permission Manager

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Computer security wikipedia , lookup

Mobile business intelligence wikipedia , lookup

Transcript
Android Application
Permission Manager
Week 8 update
Katherine Schwartz
Eralda Caushaj
This week’s overall progress
We need a dataset of known malware for testing.
• Located and gained access to known malicious apps
• Installed malicious apps on tablet
• Catalogued the features each malicious app in the correct format
Finding malicious apps
• First approach- our own list
• Found lists of apps in Google Play containing malware
• Google is too good- apps were removed before we could install!
• Where to get malicious apps?
• Looked for online repository
• Some are very outdated or no longer accessible (Ex. Android Malware
Genome Project)
Contagio mobile mini-dump
• Repository constructed by community but overseen by single
administrator
• Hundreds of malicious applications available for download
• Range from before 2012 through the newest threats
• Easy to gain access- contact administrator with legitimate reason
to get password
Using the malicious apps
• Downloaded, unzipped and installed over 200 malicious apps
(thanks Dropbox, FileDrop for Dropbox, and AndroZip!)
• Careful not to brick device/lock ourselves out!
• Used Settings and Appbrain Ad Detector to find information
• Calculated unique threats for each app
Dataset
Example section of our data.
Note:
•
Masquerading as popular apps
•
Fake “security” systems
•
“Official” looking names
First machine learning test
Testing has just begun.
•
Orange data mining software
•
10-fold cross validation
•
Default settings for each classifier
Future work
• Finally start testing machine learning models with a full dataset
• Choose and tweak a machine learning model for use in our
framework
• Rigorously test accuracy
• Plan implementation of chosen model
References
Yajin Zhou, Xuxian Jiang, "Dissecting Android Malware: Characterization
and Evolution," Proceedings of the 33rd IEEE Symposium on Security and
Privacy (Oakland 2012), San Francisco, CA, May 2012
Mila, contagio mobile. [Online]. Available:
http://contagiominidump.blogspot.com/. [Accessed: 08- Jul- 2016].
AppBrain Ad Detector. AppTornado. Available:
https://play.google.com/store/apps/details?id=com.appspot.swisscodemo
nkeys.detector
Demsar J, Curk T, Erjavec A, Gorup C, Hocevar T, Milutinovic M, Mozina M,
Polajnar M, Toplak M, Staric A, Stajdohar M, Umek L, Zagar L, Zbontar J,
Zitnik M, Zupan B (2013) ”Orange: Data Mining Toolbox in Python”. Journal
of Machine Learning Research 14(Aug):2349−2353.