Malware Detection Based on Feature Library and Machine Learning

In this paper, we propose a malware detection method based on feature library and machine learning. By using a combination of static and dynamic feature extraction method, we select 8 types of static features to build a feature library. In addition, for potentially unknown malwares, we use 9 groups of dynamic features to train a support vector machine model, and give interpretable detection results based on the influence of different features. To verify the performance of our method, we conducted various experiments on a total of 129,013 malware samples and compared the results with other schemes, demonstrating the effectiveness of our method.