Android Malware Detection Based on Image Analysis
Ke Xu, Yang Xiao Hui · 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · 2021
Aiming at the problem that the current Android malware detection methods have a single feature dimension and it is difficult to determine the multi-dimensional characteristics of the malware, this article proposes an Android malware detection method based on image analysis. This method visualizes the software's DEX file, extracts the shallow texture features and deep abstract features and combines them, and finally uses the Light Gradient Boosting Machine to detect. Experiments show that when using fusion features, the detection accuracy rate reaches 98.7%, and the effect is significantly improved compared with using a single feature.