Detection of Malicious Android Applications: Classical Machine Learning vs. Deep Neural Network Integrated with Clustering

TL;DR

This paper compares classical machine learning and deep neural networks, integrated with clustering, for Android malware detection, demonstrating that Random Forest models with clustering achieve near-perfect accuracy and improved efficiency.

Contribution

It introduces an effective malware detection approach combining Random Forest with clustering, outperforming deep neural networks in accuracy and efficiency.

Findings

Random Forest achieved 99.4% AUC without feature reduction.

Clustering with Random Forest increased AUC to 99.6%.

Feature reduction improved model efficiency significantly.

Abstract

Today anti-malware community is facing challenges due to the ever-increasing sophistication and volume of malware attacks developed by adversaries. Traditional malware detection mechanisms are not able to cope-up with next-generation malware attacks. Therefore in this paper, we propose effective and efficient Android malware detection models based on machine learning and deep learning integrated with clustering. We performed a comprehensive study of different feature reduction, classification and clustering algorithms over various performance metrics to construct the Android malware detection models. Our experimental results show that malware detection models developed using Random Forest eclipsed deep neural network and other classifiers on the majority of performance metrics. The baseline Random Forest model without any feature reduction achieved the highest AUC of 99.4%. Also, the segregating of vector space using clustering integrated with Random Forest further boosted the AUC to 99.6% in one cluster and direct detection of Android malware in another cluster, thus reducing the curse of dimensionality. Additionally, we found that feature reduction in detection models does improve the model efficiency (training and testing time) many folds without much penalty on the effectiveness of the detection model.