Integrated Malware analysis using machine learning

Abstract

Detection of malwares using unprecedented zero-day vulnerabilities is a challenging task and needs advanced analysis techniques for their classification and identification. Malware developers employ various anti-analysis techniques to evade detection and disrupt the analysis. Most malware analysts use Static and Dynamic analysis techniques to analyze malwares. However, there are Pros and Cons of using these analysis techniques. Our work proposes a solution where we have extracted selected features from the static and dynamic analysis techniques. Using the selected features, an integrated approach has been developed so that the classification and detection rate may improve compared to static and dynamic approach. We have analyzed malwares equipped with anti-analysis features for better classification and detection result. Our result shows an accuracy of 73.47% using the integrated approach, 69.72% using static and 63.30% using dynamic analysis. Comparing the static and dynamic approach, the integrated approach provides better accuracy.