| Creator |
|
|
|
|
|
| Language |
|
| Publisher |
|
|
|
| Date |
|
| Source Title |
|
| Vol |
|
| First Page |
|
| Last Page |
|
| Conference |
|
| Publication Type |
|
| Access Rights |
|
| JaLC DOI |
|
| Abstract |
Today, mobile devices are very popular in everyday life of our sociality for communication or many perspectives. They become an interesting point for malicious attackers. Malicious software which can ...destroy mobile devices or steal sensitive information are growing in every form of people’s live. A number of researches have been proposed to detect malicious software in recent year. However, they still suffer with many intelligent malicious software that a traditional methodology is not sufficient to detect the key features of intelligent malware. To address this problem, this paper proposes a feature extraction method from Android malware applications using hybrid analysis method to improve Machine Learning based detection framework. ADetect can achieve 80% detection accuracy, which are tested by using Random Forest, K-nearest Neighbor and Naïve Bayes (NB) classifiers.show more
|
Export Mendeley
p027