Please use this identifier to cite or link to this item:
https://dspace.univ-ghardaia.edu.dz/xmlui/handle/123456789/1038
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | REDDAH, Bayoub | - |
dc.contributor.author | DAOUDI, Nessreddin | - |
dc.date.accessioned | 2022-05-24T13:28:06Z | - |
dc.date.available | 2022-05-24T13:28:06Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | https://dspace.univ-ghardaia.edu.dz/xmlui/handle/123456789/1038 | - |
dc.description.abstract | Android is the most used mobile operating system in the world and since it is open source, hackers exploit it to perform different attacks such as executing botnet attack which allow them to control the compromised device remotely from a Command and control (C&C) server and perform other attacks such as distributed denial of service (DDOS) from the device itself without the owners’ knowledge. The aim of our study is to find a model that allows us to detect Android botnets efficiently. Our proposed method uses a single layer and multi-layer Perceptron models trained on 342 features to classify application as benign or botnet using ICSX dataset. We obtained great results from our experimental study with an accuracy of 99%. | EN_en |
dc.publisher | université Ghardaia | EN_en |
dc.subject | Botnet detection, Android Botnets, Mobile Botnet, Machine learning, Perceptron, Multi-layer Perceptron, Static Analysis, Smartphone Security | EN_en |
dc.title | Theme Machine Learning for smartphone security: Android botnet d | EN_en |
dc.type | Thesis | EN_en |
Appears in Collections: | Mémoires de Master |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Master_thesis.pdf | 3.61 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.