Android Ransomware Detection using Machine Learning Techniques: A Comparative Analysis on GPU and CPU
Shweta Sharma, C. Rama Krishna, Rakesh Kumar
Abstract
Cyber-criminals perform ransomware attacks to make money from victims by harming their devices. The attacks are rapidly increasing on Android-based smartphones due to its vast usage world-wide. In this paper, a framework has been proposed in which we (1) utilize novel features of Android ransomware, (2) employ machine learning models to classify ransomware and benign apps, and (3) perform a comparative analysis to calculate the computational time required by machine learning models to detect Android ransomware. Our proposed framework can efficiently detect both locker and crypto ransomware. The experimental results show that the proposed framework detects Android ransomware by achieving an accuracy of 99.59% with Logistic Regression in 177 milliseconds and 235 milliseconds on the Graphics Processing Unit (GPU) and Central Processing Unit (CPU) respectively.