Android Malware Detection with Deep Learning using RNN from Opcode Sequences

Abstract

Android is the most widely used operating system in smartphones. Mobile users can download and access apps easily from the play store. Due to lack of security awareness and risk associated with mobile apps, malware apps would be downloaded by normal users in general. The consequences after installing a malware app are unpredictable. Malware apps can gather user personal data, browsing history, user profiles, user sensitive data like passwords. Hence, android malware detection is essential for providing security to mobile users. Android malware detection using machine learning is done either by extracting static features (opcodes, permissions, intents, system commands) or by extracting dynamic features (log behavior, system calls, dataflow). In this paper, opcode sequences are extracted from malware and benign apps, and Recurrent Neural Networks are proposed on extracted sequences. Benign apps are collected from the play store, apkpure.com and malware apps are collected from the virus share website. The proposed Recurrent Neural Network model could achieve 96% accuracy for android malware detection.

Combatting ransomware in ZephyrOS-activated industrial IoT environments

“…Appropriately, in the domain of ransomware detection in IoT using ML, several research methods have been prominently employed to address the challenges posed by the intricacies of IoT data streams and evolving ransomware signatures. Supervised learning techniques, particularly deep learning models like Convolutional Neural Networks (CNNs) [10] and Recurrent Neural Networks (RNNs) [11] , are widely used due to their efficacy in recognizing patterns from large datasets. Feature selection and extraction, a crucial pre-processing step, often involve techniques like Principal Component Analysis (PCA) [12] and the t-distributed Stochastic Neighbor Embedding (t-SNE) [13] to reduce data dimensionality while retaining essential information.…”

Android applications classification with deep neural networks

“…Deep neural network approaches have recently been the subject of numerous studies on extending machine learning techniques for unlabelled data. For instance,Lakshmanarao et al [22] recently targeted specific opcode sequences extracted from android applications dataset to train a recurrent neural network for malware classification. Fallah et al [23] modeled an instance of traffic data as a series of flows by using long Short Term memory(LSTM) model for malware detection and classification into legitimate and malicious samples.…”