Machine learning approach to detect android malware using feature-selection based on feature importance score

Abstract

The hazards posed by malware are proliferating along with technology’s rapid advancement and the use of online services. Specifically, attacks on Android devices are growing enormously because of the boost in the popularity of Smartphones. Existing research confirms that identifying benign or malware applications on the Android platform is possible by analysing the permissions through the machine-learning classifier. There are machine-learning techniques that create models to detect Android malware using permission-based attributes. However, further research is still needed to develop effective feature selection strategies for malware detection mechanisms in Android. In this study, a machine-learning-based Android malware detection mechanism is proposed, and standard machine-learning algorithms are used on multiple permission-based datasets to classify malware. This study suggests a feature selection method that uses the feature importance score computed using Gradient boosting to identify the essential permissions. The proposed methodology decreases the feature vector’s dimension, reducing the model’s training time. We also compare the classifier’s performance with the complete feature set and with the reduced feature set. Examining the results, we notice that the algorithm’s execution time improved significantly for all datasets with negligible loss in accuracy.