ACAMA: Deep Learning-Based Detection and Classification of Android Malware Using API-Based Features

Abstract

As a great number of IoT and mobile devices are used in our daily lives, the security of mobile devices is being important than ever. If mobile devices which play a key role in connecting devices are exploited by malware to perform malicious behaviors, this can cause serious damage to other devices as well. Hence, a huge research effort has been put forward to prevent such situation. Among them, many studies attempted to detect malware based on APIs used in malware. In general, they showed the high accuracy in detecting malware, but they could not classify malware into detailed categories because their detection mechanisms do not consider the characteristics of each malware category. In this paper, we propose a malware detection and classification approach, named ACAMA, that can detect malware and categorize them with high accuracy. To show the effectiveness of ACAMA, we implement and evaluate it with previously proposed approaches. Our evaluation results demonstrate that ACAMA detects malware with 26% higher accuracy than a previous work. In addition, we show that ACAMA can successfully classify applications that another previous work, AVClass, cannot classify.

Novel Ransomware Detection Exploiting Uncertainty and Calibration Quality Measures Using Deep Learning

“…Additionally, DBNs have been utilized in extracting invariant representations of malware behavior, as evidenced by [16], exposing the adaptability of DBNs to capture complex malware behavior patterns. Moreover, DBNs have been demonstrated to be instrumental in Android malware detection with studies by [44,45] which demonstrated the efficacy of DBNs in processing static features and enhancing detection accuracy. The application of DBNs in cybersecurity extends to the detection of intrusions and malware, as highlighted by [46], emphasizing the broad utility of DBNs in safeguarding systems against cyber threats.…”

A novel method of detecting malware on Android mobile devices with explainable artificial intelligence

“…Abubaker et al [4] gives framework that uses feature selection based on an ensemble extra tree classifier approach and a machine learning classifier to examine the behavior of malware apps by evaluating permissions. When it comes to detecting and classifying malware, a method has been presented [5]. DL-droid is a deep learning system that can detect malicious android apps by methodical input generation and dynamic analysis [6].…”