Android Malware Detection Technology Based on Lightweight Convolutional Neural Networks

Abstract

With the rapid development of Android, a major mobile Internet platform, Android malware attacks have become the number one threat to mobile Internet security. Traditional malware detection methods have low precision and greater time complexity. At present, image detection methods based on deep learning are used in malware detection. However, most of these methods are based on the largescale convolutional neural network model (such as VGG16). The computation and weight files of these models are very large, so they are not suitable for mobile Internet platforms with limited computation. A novel detection method based on a lightweight convolutional neural network is presented in this study. It transforms Android malware classes.dex, Androidmanifest.xml, and resource.arsc into RGB images and uses the lightweight convolutional neural network to extract the features of RGB images automatically. The experimental results of this study indicate that the method performs well in terms of precision and speed of detection.

Retracted: Visualisation‐based binary classification of android malware using vgg16

“…The authors in Ref. [16] focus on Deep learning/Convolutional Network-based method for detecting Android malwares. Since deep learning models such as CN networks have a tendency to outstand, in terms of performance and accuracy especially when it comes to image recognition as compared to the old traditional machine learning models, CNN offers a much more reliable and accurate approach for obtaining higher-level image features since it is a multilayered mechanism (including the input layer, the convolution layer, the ReLU excitation layer, the pooling layers and fully connected layers).…”

Robust convolutional neural network with integrated multiscale attention mechanism against adversarial attacks

“…Deep neural networks (DNNs) are widely used in various fields due to their powerful performance: autonomous driving, speech recognition, anomaly detection, infrared target detection, EEG signal analysis, malware detection, etc. In recent years, DNNs have been widely used in the field of image classification due to their ability to reduce the workload of doctors, reduce the error rate, and improve the efficiency of detection [1,2,3,4,5,6]. DNNs have evolved to produce a wide range of network models, and their performance has been gradually optimized to outperform the original for specific domains.…”