AyatDroid: a lightweight code cloning technique using different static features

Abstract

In recent decades, malicious code reuse has surged in numbers and sophistication, it is a common practice among adversaries to reuse malicious code, which significantly threatens user privacy and security. Several signature-based code clone detection techniques have been proposed to detect malicious clones in Android applications that use the MD5 hash function to generate signatures. Meanwhile, these techniques only retrieve signatures from Java files. Due to the 128-bit signature size of the MD5 hash function, these techniques take longer to generate signatures. In this article, we propose the AyatDroid technique, which efficiently identifies malicious chunks by retrieving signatures from Java and manifest files. AyatDroid technique is tested on reliable CiCMalDroid 2020 dataset. We have evaluated the AyatDroid technique with other cutting-edge code clone detection techniques. Our experimental results demonstrated that AyatDroid outperformed regarding detection time and accuracy. AyatDroid is not only lightweight but also efficient, allowing it to be implemented on the large scale.