@article{MAKHILLJEAS2019142318701,
    title = {A Deep Neural Network Classifier for Android Malwares Detection
using Feature Combination},
    journal = {Journal of Engineering and Applied Sciences},
    volume = {14},
    number = {23},
    pages = {8761-8768},
    year = {2019},
    issn = {1816-949x},
    doi = {jeasci.2019.8761.8768},
    url = {https://makhillpublications.co/view-article.php?issn=1816-949x&doi=jeasci.2019.8761.8768},
    author = {Saman},
    keywords = {Android mobile,malwares,deep neural classifiers,feature combination,feedforward,detection
model},
    abstract = {Cases of Android security defence system penetration has increasedin recent years. This increase
has prompted the investigation and evaluation of the execution behaviours of malicious applications in mobile
systems, especially, Android Operating Systems (OSs). The main challenge of the detection systems is making
many false alarms which are related to misclassifying the malicious behaviours as normal. This study proposes
a new approach that combines the Android mobile features for targeting malwares and uses a deep feed forward
neural network for detecting malicious activities or behaviours. The study employs different sets of mobile
malware features to train and test the detection model. Results showed improved accuracy of detection rates
when the detection model is trained with combined features.}
    }